gsd-audit-uat
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it is designed to ingest and process the contents of markdown files within the codebase.
- Ingestion points: The skill reads files matching the globs
.planning/phases/*/*-UAT.mdand.planning/phases/*/*-VERIFICATION.md. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within these files.
- Capability inventory: The skill is configured with access to
Read,Glob,Grep, andBashtools. - Sanitization: There is no evidence of sanitization or filtering applied to the ingested content before processing.
- [EXTERNAL_DOWNLOADS]: The skill references an external workflow configuration located at
~/.claude/gsd-core/workflows/audit-uat.md. This path resides within the local environment and is consistent with the developer's ('open-gsd') internal tooling structures; it does not represent an unauthorized remote download or execution of third-party code.
Audit Metadata