skills/ab300819/skills/devdocs-verify/Gen Agent Trust Hub

devdocs-verify

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it reads and analyzes content from external documentation and source code files.
  • Ingestion points: Content is read from '01-requirements.md', '02-system-design.md', and '03-test-cases.md'.
  • Boundary markers: The skill does not implement specific delimiters or warnings to ignore embedded instructions within processed files.
  • Capability inventory: The skill uses 'Bash', 'Read', 'Glob', and 'Grep' to perform its verification tasks.
  • Sanitization: No content validation or filtering of input files is mentioned.
  • [COMMAND_EXECUTION]: Uses the 'Bash' tool to execute local verification logic and generate report files, which is consistent with its stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill optionally uses well-known browser automation tools (Playwright, Chrome DevTools) for UI verification, which are considered trusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 06:08 AM