gsd-ai-integration-phase
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and metadata do not contain any malicious patterns, obfuscation, or unauthorized access attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests phase numbers from arguments and content from
ROADMAP.md. This is a standard data ingestion point for the intended workflow of orchestrating project phases and does not involve unsafe interpolation or command execution of untrusted data. - [DATA_EXPOSURE]: The skill references files within
~/.claude/gsd-core/, which appear to be internal framework references for the 'open-gsd' vendor. No exposure of sensitive user credentials or system secrets was detected.
Audit Metadata