test-quality-audit
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill outlines a methodology for assessing test suites, emphasizing the identification of tests that protect user-visible behavior over simple coverage metrics. The instructions are focused on development best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading and analyzing implementation code, pull request metadata, and bug reports (SKILL.md, "What to read"). This establishes an ingestion surface for potentially untrusted data. Additionally, the skill permits the agent to execute test commands and modify files in a temporary environment. While the skill lacks explicit boundary delimiters or sanitization steps, these capabilities are inherent to the intended primary purpose of a code-auditing tool and do not demonstrate malicious intent.
Audit Metadata