gsp-doctor

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs diagnostic checks on project files located in .design/ and verifies the health of the local installation within ~/.claude/skills/. It uses standard tools (Bash, Read, Glob, Grep) for these tasks. All identified command execution is legitimate for a diagnostic tool and involves no privilege escalation or persistence mechanisms.
  • [SAFE]: Indirect Prompt Injection Analysis:
  • Ingestion points: The skill reads various project documentation files (e.g., BRIEF.md, STATE.md, INDEX.md) which could potentially contain untrusted content.
  • Boundary markers: None present.
  • Capability inventory: Bash, Read, Glob, Grep.
  • Sanitization: Not implemented; however, the skill is explicitly constrained to deterministic, read-only pattern matching tasks, which minimizes the risk of executing instructions embedded in data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 04:01 AM