review-docs
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests markdown documentation files for review, creating an attack surface for indirect prompt injection where malicious content within the documentation could attempt to influence the agent's behavior. . Ingestion points: Markdown files read via the Read tool. . Boundary markers: None identified in the skill instructions to isolate untrusted content. . Capability inventory: Subagent spawning (Agent tool), shell execution (Bash), and file system access (Read, Grep, Glob). . Sanitization: No filtering or escaping is applied to the content of the documentation files before processing.
- [COMMAND_EXECUTION]: The skill executes shell commands and local scripts as part of its automated checking process. . Evidence: SKILL.md and process.md reference the execution of git status, pnpm lint:md, and a local vendor-provided script .agents/skills/review-docs/scripts/check-frontmatter.sh. It also suggests performing git checkout on potentially user-supplied branch names when reviewing pull requests.
Audit Metadata