gsd-ai-integration-phase
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes local workflow and reference files located in
~/.claude/gsd-core/. These paths are consistent with the 'open-gsd' vendor resource patterns and represent standard configuration rather than sensitive system file access. - [PROMPT_INJECTION]: The skill is designed to ingest external data which could serve as a vector for indirect prompt injection.
- Ingestion points: User-provided phase numbers via
$ARGUMENTSand project status fromROADMAP.md(via workflow orchestration). - Boundary markers: None specified in the instructions to delimit untrusted data.
- Capability inventory: The skill uses
Bash,Write,Agent, andWebSearchtools to perform its tasks. - Sanitization: No explicit input validation or sanitization of ingested content is defined.
Audit Metadata