pdm
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze content from external and potentially untrusted project artifacts.
- Ingestion points: As detailed in
SKILL.mdandreference/source-triangulation.md, the agent reads fromdocs/**/*.md,ROADMAP.md,CHANGELOG.md, and issue trackers usinggh issue list. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded within the ingested planning artifacts.
- Capability inventory: The skill performs local file reads and executes
ghCLI commands to fetch project metadata. - Sanitization: The instructions do not include logic for sanitizing or filtering out instructions contained within the ingested documentation or issues.
Audit Metadata