troubleshooting
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard triage workflow for identifying and resolving development errors. It employs common local commands like
pnpm run test,node --version, andgit lfs envto gather diagnostics. These actions are appropriate for the skill's purpose and do not involve unauthorized network calls or privilege escalation. - [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for the agent to ingest local project documentation. While this is an ingestion surface, the risk is managed by the development team's control over internal project files and does not expand the agent's capability set. 1. Ingestion points: Reads local markdown documentation files (e.g.,
projects/site/src/docs/internal/guidelines/troubleshooting.md). 2. Boundary markers: Not explicitly defined in the skill instructions. 3. Capability inventory: Execution of local testing and build scripts viapnpmas defined in the diagnostic triage workflow. 4. Sanitization: Not explicitly implemented in the skill instructions.
Audit Metadata