skills/rmyndharis/antigravity-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 Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill is susceptible to indirect prompt injection because it processes untrusted external code provided through the $ARGUMENTS variable without defined sanitization or boundary markers. 1. Ingestion points: External data enters the context via file paths, Git repositories, and code snippets. 2. Boundary markers: Absent; there are no instructions to the agent to distinguish between its own logic and instructions that might be embedded in the code being reviewed. 3. Capability inventory: The skill facilitates reading and analyzing project structures and file contents. 4. Sanitization: Absent; no validation or escaping of the target code is implemented.
Audit Metadata