skills/sickn33/antigravity-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 Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted code and projects without sufficient boundary markers or sanitization.
- Ingestion points: The skill accepts code snippets, file paths, and Git repositories via the
$ARGUMENTSparameter as described in SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the code being reviewed and potential instructions embedded within that code.
- Capability inventory: The orchestration logic includes identifying code context, routing tasks to specialized agents (e.g., security auditors, performance analysts), and synthesizing combined reports.
- Sanitization: The skill lacks logic or instructions for validating, escaping, or filtering content ingested from the target code to prevent instruction override.
Audit Metadata