gsd-ingest-docs
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest, synthesize, and merge content from potentially untrusted external repository documents (ADRs, PRDs, specs, and docs).
- Ingestion points: Discovers and reads files from directory conventions like
docs/adr/,docs/prd/, etc., or an explicit manifest (SKILL.md). - Boundary markers: While it mentions a 'shared conflict engine' and 'BLOCKER gate' for logical contradictions, it lacks explicit structural delimiters or warnings to the LLM to ignore instructions embedded within the ingested document content.
- Capability inventory: The skill is granted access to high-privilege tools including
Bash,Write,Edit, andAgent(SKILL.md). - Sanitization: No evidence of content sanitization, filtering, or escaping for the ingested documentation is provided in the skill definition.
Audit Metadata