quality-guardian
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard development lifecycle commands (
pnpm lint,pnpm typecheck,pnpm test) using theterminaltool. These commands are intended to audit local project code and are appropriate for the skill's stated purpose. - [PROMPT_INJECTION]: The skill was evaluated for Indirect Prompt Injection (Category 8) because it ingests and analyzes output from external tools (stdout/stderr). While this represents a potential attack surface if a developer's code or tests output malicious instructions, no evidence of such patterns was found, and the behavior is inherent to the skill's primary function.
- Ingestion points: terminal tool stdout/stderr output (SKILL.md)
- Boundary markers: Not present
- Capability inventory: full shell access via
terminaltool - Sanitization: Not present
Audit Metadata