菜单
Discover an organization's public exposures — leaked credentials and secrets, exposed services and storage, source-code/config leaks, and breach data — from public sources. Use to find what's already exposed about a target (offense) or to reduce your own exposure (defense). Authorized scope.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Statically review a Claude Code / AI-agent setup for security misconfigurations — risky hooks, over-broad permissions, untrusted or cleartext MCP servers, hardcoded secrets, endpoint redirection, over-privileged agents/skills, and prompt-injection in steering files. Use when asked to audit a `.claude/` directory, `settings.json`, `.mcp.json`, a plugin/marketplace, or `CLAUDE.md`, or to add a config-security gate to CI. Drives the `agentscanner` CLI.
Review the training / MLOps pipeline for security weaknesses — data-poisoning surface, feature-store and data-source trust, experiment-tracking and model-registry access control, secrets, and reproducibility/provenance. Use when assessing how models are built and promoted, not how they're served or consumed.
Review the provenance and integrity of models, datasets, and ML artifacts pulled from hubs/registries — unsafe deserialization (pickle, PyTorch/Keras/joblib), untrusted model sources, model/dataset tampering, and signing. Use when an app loads third-party model weights or datasets, or before promoting a model.
Harden a deployed model inference endpoint — authn/authz, rate limiting and abuse control, input validation, and exposure to model-extraction / inversion / membership-inference attacks. Use when reviewing how a model is served (REST/gRPC, Triton/TorchServe/KServe, or a hosted inference API), not how it was trained.
Export a finished security artifact (report, executive summary, diagram, spreadsheet of findings) to Google Drive — right folder, clear naming, and shareable with the intended audience. Use when a deliverable needs to be handed to stakeholders who live in Drive/Docs/Sheets rather than a wiki or tracker.
Turn a security finding (vuln, pentest issue, review item) into a well-formed Jira issue — mapped severity→priority, remediation/repro in the body, labels and components set, and dedup-checked against existing issues. Use when findings need to become tracked, assignable work in Jira.
| name | exposure-discovery |
| description | Discover an organization's public exposures — leaked credentials and secrets, exposed services and storage, source-code/config leaks, and breach data — from public sources. Use to find what's already exposed about a target (offense) or to reduce your own exposure (defense). Authorized scope. |
A prioritized list of real public exposures that an attacker could use immediately, with the action to remediate or exploit (within scope) each.
An exposure list: exposure · type · source · validity/confidence · impact · action
(rotate/revoke/remove/harden). Confirmed exposures → security-reporting:finding
(live credentials and exposed data = high+). Defensively, feed an ASM remediation plan.
Validate before acting — many "leaks" are stale or recycled. Treat found credentials as rotate/revoke items; do not authenticate with them unless the engagement explicitly authorizes it. Secrets in git history and public buckets are the most common high-impact exposures.
