Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

reachability-triage

Estrellas1

Forks0

Actualizado30 de mayo de 2026 a las 20:38

Triage a candidate finding by deciding whether the vulnerable code is reachable from an untrusted entry point, producing the reachability axis (0-1) that feeds asec-confidence. Use when the user asks to triage a finding or assess exploitability.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

theagenticguy

theagenticguy/agentic-security-lab

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Analistas de seguridad de la informaciónOcupaciones informáticas y matemáticas·SOC 15-1212

SKILL.md

readonly

name	reachability-triage
description	Triage a candidate finding by deciding whether the vulnerable code is reachable from an untrusted entry point, producing the reachability axis (0-1) that feeds asec-confidence. Use when the user asks to triage a finding or assess exploitability.
allowed-tools	Read Grep Glob Bash(git diff ) Bash(semgrep )
argument-hint	["finding-file-or-location"]
context	fork
agent	general-purpose

Finding under triage

@$ARGUMENTS[0]

Task (v1.2 spec)

Identify the sink: the exact file:line and the dangerous operation (the candidate CWE).
Identify untrusted sources: external entry points (HTTP handlers, CLI args, deserialized input, message consumers). Enumerate them from entrypoints and route/handler registration.
Trace call paths from each source to the sink using Grep/Read (and semgrep taint queries when available). Record the shortest concrete path or prove none exists.
Classify reachability:
- 1.0 — direct, unconditional path from an untrusted source to the sink.
- 0.6-0.9 — reachable but guarded (auth, validation, feature flag); note the guard.
- 0.1-0.5 — reachable only via an unlikely or internal-only path.
- 0.0 — no path from any untrusted source (dead code, test-only, fully gated).
Note sanitizers/validators on the path that would neutralize the input, and whether they are complete.

Emit a JSON block matching the reachability field of asec_confidence.ConfidenceInputs:

{"reachability": 0.0, "sink": "file:line", "sources": ["..."], "path": ["..."], "guards": ["..."], "rationale": "..."}

This axis is one of three (pattern, recall, reachability) the BaselineStrategy weights; it owns the reachability portion of E18. Do not modify source files. Report only.

Más de este repositorio

mismo repositorio

variant-analysis

theagenticguy/agentic-security-lab

Big-Sleep variant analysis. Given a recently-fixed bug shape (the lines added/removed in a patch), find more code in the repository that has the same shape and is likely to carry the same defect. Reports variants linked to their seed. Deny-by-default: only the allowed_tools below are permitted.

2026-06-011

security-code-review

theagenticguy/agentic-security-lab

Review a code diff or corpus for security vulnerabilities grounded in the supplied threat model. Reads code semantically, forms hypotheses, verifies them, and emits scored findings as a single JSON code block. Deny-by-default: only the allowed_tools below are permitted.

2026-06-011

threat-model-bootstrap

theagenticguy/agentic-security-lab

Given an architecture description or diagram, produce a STRIDE threat model plus attack trees as YAML. Use when the user asks to threat model a system.

2026-05-311

security-code-review

theagenticguy/agentic-security-lab

Review a git diff for vulnerabilities by running Semgrep and CodeQL, then emit structured findings. Use when the user asks for a security review of a diff/PR.

2026-05-301

threat-model-bootstrap

theagenticguy/agentic-security-lab

Given an architecture description, diagram, or repo, produce a Phase-Zero STRIDE threat model plus attack trees as YAML conforming to asec-threat-model schema. Use when the user asks to bootstrap or create a threat model for a system.

2026-05-301

threat-model-critic

theagenticguy/agentic-security-lab

Critique an existing threat model for completeness and rigor — missing STRIDE categories, unjustified skips, weak mitigations, ungrounded likelihood/impact. Use when the user asks to review, critique, or red-team a threat-model.yaml.

2026-05-301

name	reachability-triage
description	Triage a candidate finding by deciding whether the vulnerable code is reachable from an untrusted entry point, producing the reachability axis (0-1) that feeds asec-confidence. Use when the user asks to triage a finding or assess exploitability.
allowed-tools	Read Grep Glob Bash(git diff ) Bash(semgrep )
argument-hint	["finding-file-or-location"]
context	fork
agent	general-purpose

Finding under triage

@$ARGUMENTS[0]

Task (v1.2 spec)

Identify the sink: the exact file:line and the dangerous operation (the candidate CWE).
Identify untrusted sources: external entry points (HTTP handlers, CLI args, deserialized input, message consumers). Enumerate them from entrypoints and route/handler registration.
Trace call paths from each source to the sink using Grep/Read (and semgrep taint queries when available). Record the shortest concrete path or prove none exists.
Classify reachability:
- 1.0 — direct, unconditional path from an untrusted source to the sink.
- 0.6-0.9 — reachable but guarded (auth, validation, feature flag); note the guard.
- 0.1-0.5 — reachable only via an unlikely or internal-only path.
- 0.0 — no path from any untrusted source (dead code, test-only, fully gated).
Note sanitizers/validators on the path that would neutralize the input, and whether they are complete.

Emit a JSON block matching the reachability field of asec_confidence.ConfidenceInputs:

{"reachability": 0.0, "sink": "file:line", "sources": ["..."], "path": ["..."], "guards": ["..."], "rationale": "..."}

This axis is one of three (pattern, recall, reachability) the BaselineStrategy weights; it owns the reachability portion of E18. Do not modify source files. Report only.