skills/sickn33/agentic-awesome-skills/performance-testing-review-multi-agent-review/Gen Agent Trust Hub
performance-testing-review-multi-agent-review
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no executable scripts, commands, or network operations. It provides high-level guidelines for agent behavior during code reviews, emphasizing reproduction and evidence-based findings without introducing new security risks.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process untrusted data (code diffs and repository content), which presents a potential surface for indirect prompt injection.
- Ingestion points: Instructions in
SKILL.mddirect the agent to read repository diffs and call paths from external repositories. - Boundary markers: The instructions do not define specific delimiters or escaping mechanisms to separate untrusted code content from instructions.
- Capability inventory: The skill instructs the agent to reproduce findings, which relies on the agent's existing toolset (e.g., shell or test runners) rather than bundled code.
- Sanitization: No explicit sanitization or input validation steps are provided for the processed diffs.
Audit Metadata