Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

ai-risk-mapper

Étoiles2

Forks0

Mis à jour6 mai 2026 à 17:16

This skill should be used when identifying, analyzing, and mitigating security risks in Artificial Intelligence systems using the CoSAI (Coalition for Secure AI) Risk Map framework. Use when users ask to "assess AI security risks", "analyze AI system threats", "map risks to controls", "run a risk assessment", "check compliance with MITRE ATLAS", "generate a CoSAI report", or "profile persona risks". Supports LLM applications, ML pipelines, model training/serving infrastructure, and compliance reporting aligned with MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLM, STRIDE, and ISO 22989 frameworks. Do NOT use for general software security scanning without an AI/ML component (use standard SAST/DAST tools instead).

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

totallyGreg

totallyGreg/claude-mp

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en sécurité de l'informationProfessions informatiques et mathématiques·SOC 15-1212

Explorateur de fichiers

47 fichiers

SKILL.md

readonly

name	ai-risk-mapper
description	This skill should be used when identifying, analyzing, and mitigating security risks in Artificial Intelligence systems using the CoSAI (Coalition for Secure AI) Risk Map framework. Use when users ask to "assess AI security risks", "analyze AI system threats", "map risks to controls", "run a risk assessment", "check compliance with MITRE ATLAS", "generate a CoSAI report", or "profile persona risks". Supports LLM applications, ML pipelines, model training/serving infrastructure, and compliance reporting aligned with MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLM, STRIDE, and ISO 22989 frameworks. Do NOT use for general software security scanning without an AI/ML component (use standard SAST/DAST tools instead).
metadata	{"version":"5.2.2","author":"J. Greg Williams"}
compatibility	Requires python3 and uv for script execution
license	Apache 2.0

AI Risk Mapper

When Invoked

Automated Assessment

For requests like "Analyze security risks in [target]" or "Generate a CoSAI risk assessment":

uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/orchestrate_risk_assessment.py \
  --target <user_specified_target> \
  --output-dir ./risk-assessment-output

The orchestrator automatically:

Fetches/caches CoSAI schemas (or uses offline fallback)
Analyzes target for applicable risks
Generates comprehensive assessment report
Presents findings to user

Interactive Exploration

For ad-hoc queries, threat modeling, or compliance mapping, use the CLI scripts. All support --offline flag for bundled schema usage.

Purpose	Script
Search risks by keyword	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_risk_search.py "injection"`
Search controls by keyword	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_control_search.py "training"`
Get controls for a risk	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_controls_for_risk.py DP`
Get persona risk profile	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_persona_profile.py personaModelProvider`
Assess control coverage	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_gap_analysis.py DP --implemented controlTrainingDataSanitization`
Get framework mappings	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_framework_map.py PIJ --framework mitre-atlas`
Risks by actor access level	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_actor_access.py agent`

See references/exploration_guide.md for entity IDs, query patterns, and the core analyzer API.

Error Handling & Fallback

Network/SSL Failures: Orchestrator automatically switches to bundled offline schemas — workflow continues without user intervention.

Manual offline mode:

uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/orchestrate_risk_assessment.py --target <path> --offline

Missing Target: Ask user: "Please specify a file, directory path, or brief system description to analyze"

Reference Pointers

Topic	Reference
Framework fundamentals	`references/cosai_overview.md`
Persona definitions	`references/personas_guide.md`
Risk & schema structures	`references/schemas_reference.md`
Data collection forms	`references/forms.md`
Workflow procedures	`references/workflow_guide.md`
Interactive exploration	`references/exploration_guide.md`
Usage examples	`references/usage_examples.md`
Threat actor access levels	`references/actor_access_guide.md`

Resources

Automation Scripts: (via ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/)

orchestrate_risk_assessment.py - Workflow orchestrator
fetch_cosai_schemas.py - Schema downloader
analyze_risks.py - Risk identification engine
generate_report.py - Report generator
core_analyzer.py - Core query API (30+ methods)

Interactive CLI: (via ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/)

cli_risk_search.py - Search risks
cli_control_search.py - Search controls
cli_controls_for_risk.py - Controls for risk
cli_persona_profile.py - Persona profiles
cli_gap_analysis.py - Gap analysis
cli_framework_map.py - Framework mappings
cli_actor_access.py - Risks by actor access level

Bundled Assets: (via ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/)

assets/cosai-schemas/ - Offline schema cache
assets/report_template.md - Report template

External Framework: https://github.com/cosai-oasis/secure-ai-tooling

Plus depuis ce dépôt

même dépôt

handoff

totallyGreg/claude-mp

This skill should be used when the user or another agent asks to "create a handoff", "write a handoff payload", "generate a handoff for another agent", "build a context handoff", "configure a tmux relay", "hand off this work", "hand off to another claude", "relay this to another agent", "send context to a teammate", "transfer this to another pane", "pass this to <agent-name>", "/handoff", or otherwise wants to transfer structured work context from this Claude session to another Claude — whether a teammate spawned via SendMessage, a Claude process running in a separate tmux pane, or via clipboard for human-mediated handoff. Do NOT use for tmux pane management generally (use terminal-guru) or for end-of-session file-based recap intended for a future fresh Claude session unrelated to any live recipient (that is a different problem domain).

2026-07-012

mise-tooling

totallyGreg/claude-mp

This skill should be used when the user asks to "configure mise.toml", "create a mise task", "set up tool versions", "manage environments with mise", "debug mise config", "task_config includes", "mise task DRY", "mise profiles", "mise env not loading", "create mise run command", or needs help with mise (jdx/mise) for tool versioning, environment variables, or task automation. Also trigger on mentions of mise.toml, .miserc.toml, mise run, mise env, mise tasks, mise profiles, task_config, or exec() in env. Do NOT use for shell configuration or function generation (use zsh-dev instead). Do NOT use for sesh/tmux session management (use environment-composition instead). Do NOT use for signal handling or logging (use signals-monitoring instead). Mise + sesh integration questions should route here for the mise side and environment-composition for the sesh side.

2026-06-302

wtf

totallyGreg/claude-mp

This skill should be used PROACTIVELY to "create a friction report", "check for broken tooling", or "run a friction check" when you hit confusing errors, bad docs, missing prereqs, broken tools, misleading skills, flaky tests, auth/MCP failures, or any "this should've been easier" moment. Also trigger when the user says "file an issue", "report this friction", "log this feedback", "wtf", or "this should be easier". Do NOT use for fixing the friction itself (use skillsmith or agentsmith instead).

2026-06-252

omnifocus-core

totallyGreg/claude-mp

This skill should be used when querying OmniFocus data, managing tasks, running GTD diagnostics, or configuring perspectives. Triggers when user asks "show tasks", "overdue items", "check inbox", "stalled projects", "waiting for list", "someday maybe", "GTD health check", "AI Agent tasks", "publish plan to OmniFocus", "set up perspectives", "perspective inventory", "configure perspective", "quick stats", or "missing perspectives". Also triggers when the user pastes an `omnifocus://` URL — parse the entity type and ID from the URL, then use `/ofo:info <url>` to look it up directly. Do NOT trigger for: "create OmniFocus plugin" (use omnifocus-generator skill), "analyze my system" or "discover my patterns" (use attache-analyst skill), pure GTD methodology questions (use gtd-coach skill).

2026-06-252

attache-analyst

totallyGreg/claude-mp

This skill should be used when analyzing OmniFocus system structure, discovering workflow patterns, running AI-enhanced GTD coaching, or learning the user's tool stack. Triggers when user asks "analyze my OmniFocus", "discover my system", "what's my structure", "AI coaching", "project health analysis", "system insights", "learn my workflow", "understand my patterns", "suggest improvements", "what tools do I use", or "update my tool stack". Do NOT trigger for: "show tasks" or "check inbox" (use omnifocus-core), "create OmniFocus plugin" (use omnifocus-generator), "what makes a good next action" (use gtd-coach for pure methodology). This skill is read-only against OmniFocus. It discovers patterns, infers structure, and persists learned insights via the Attache preferenceManager. It can read and update vault tool notes (status, usage patterns) via the archivist agent.

2026-06-172

omnifocus-generator

totallyGreg/claude-mp

This skill should be used when creating OmniFocus Automation plugins (.omnifocusjs), JXA scripts for OmniFocus, or OmniFocus automation artifacts. Triggers when user asks "create OmniFocus plugin", "generate OmniFocus plugin", "build .omnifocusjs", "build OmniFocus automation", "build JXA script for OmniFocus", "create OmniFocus action", or "make OmniFocus plugin". Do NOT trigger for: "create a plugin" without OmniFocus context (ask for clarification), "create a Claude plugin" (use plugin-dev skill), "install a plugin" (use omnifocus-core skill), "show tasks" or "analyze" (use omnifocus-core skill). WORKFLOW: 1) CLASSIFY query vs plugin 2) SELECT format (solitary/solitary-fm/bundle/solitary-library) 3) COMPOSE from libraries 4) GENERATE via `node scripts/generate_plugin.js` - NEVER Write/Edit tools 5) VALIDATE via `bash scripts/validate-plugin.sh` 6) TEST in OmniFocus.

2026-06-162

name	ai-risk-mapper
description	This skill should be used when identifying, analyzing, and mitigating security risks in Artificial Intelligence systems using the CoSAI (Coalition for Secure AI) Risk Map framework. Use when users ask to "assess AI security risks", "analyze AI system threats", "map risks to controls", "run a risk assessment", "check compliance with MITRE ATLAS", "generate a CoSAI report", or "profile persona risks". Supports LLM applications, ML pipelines, model training/serving infrastructure, and compliance reporting aligned with MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLM, STRIDE, and ISO 22989 frameworks. Do NOT use for general software security scanning without an AI/ML component (use standard SAST/DAST tools instead).
metadata	{"version":"5.2.2","author":"J. Greg Williams"}
compatibility	Requires python3 and uv for script execution
license	Apache 2.0

AI Risk Mapper

When Invoked

Automated Assessment

For requests like "Analyze security risks in [target]" or "Generate a CoSAI risk assessment":

uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/orchestrate_risk_assessment.py \
  --target <user_specified_target> \
  --output-dir ./risk-assessment-output

The orchestrator automatically:

Fetches/caches CoSAI schemas (or uses offline fallback)
Analyzes target for applicable risks
Generates comprehensive assessment report
Presents findings to user

Interactive Exploration

For ad-hoc queries, threat modeling, or compliance mapping, use the CLI scripts. All support --offline flag for bundled schema usage.

Purpose	Script
Search risks by keyword	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_risk_search.py "injection"`
Search controls by keyword	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_control_search.py "training"`
Get controls for a risk	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_controls_for_risk.py DP`
Get persona risk profile	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_persona_profile.py personaModelProvider`
Assess control coverage	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_gap_analysis.py DP --implemented controlTrainingDataSanitization`
Get framework mappings	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_framework_map.py PIJ --framework mitre-atlas`
Risks by actor access level	`uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/cli_actor_access.py agent`

See references/exploration_guide.md for entity IDs, query patterns, and the core analyzer API.

Error Handling & Fallback

Network/SSL Failures: Orchestrator automatically switches to bundled offline schemas — workflow continues without user intervention.

Manual offline mode:

uv run ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/orchestrate_risk_assessment.py --target <path> --offline

Missing Target: Ask user: "Please specify a file, directory path, or brief system description to analyze"

Reference Pointers

Topic	Reference
Framework fundamentals	`references/cosai_overview.md`
Persona definitions	`references/personas_guide.md`
Risk & schema structures	`references/schemas_reference.md`
Data collection forms	`references/forms.md`
Workflow procedures	`references/workflow_guide.md`
Interactive exploration	`references/exploration_guide.md`
Usage examples	`references/usage_examples.md`
Threat actor access levels	`references/actor_access_guide.md`

Resources

Automation Scripts: (via ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/)

orchestrate_risk_assessment.py - Workflow orchestrator
fetch_cosai_schemas.py - Schema downloader
analyze_risks.py - Risk identification engine
generate_report.py - Report generator
core_analyzer.py - Core query API (30+ methods)

Interactive CLI: (via ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/scripts/)

cli_risk_search.py - Search risks
cli_control_search.py - Search controls
cli_controls_for_risk.py - Controls for risk
cli_persona_profile.py - Persona profiles
cli_gap_analysis.py - Gap analysis
cli_framework_map.py - Framework mappings
cli_actor_access.py - Risks by actor access level

Bundled Assets: (via ${CLAUDE_PLUGIN_ROOT}/skills/ai-risk-mapper/)

assets/cosai-schemas/ - Offline schema cache
assets/report_template.md - Report template

External Framework: https://github.com/cosai-oasis/secure-ai-tooling