documentation-update

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute various documentation toolchains and validation commands, such as sphinx-build, mkdocs, and npm-based scripts (e.g., npm run docs). These commands rely on configuration and logic defined within the target repository, which may contain untrusted build instructions.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing external documentation and configuration files that could contain malicious instructions.\n
  • Ingestion points: Local repository documentation files (README.md, docs/*.md), API reference definitions, and project configuration files (e.g., package.json, mkdocs.yml, typedoc.json) as identified in SKILL.md and references/documentation.md.\n
  • Boundary markers: Not present. The instructions do not specify any delimiters or warnings to ignore instructions or commands embedded within the files being processed.\n
  • Capability inventory: Execution of shell commands for documentation generation, file system read/write access for updates, and repository-wide searching using rg (ripgrep).\n
  • Sanitization: Absent. Content from documentation files is used directly for updates and validation checks without any validation or sanitization of potential instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 11:54 AM
Security Audit — agent-trust-hub — documentation-update