code-quality-engine
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted application and library code, creating a potential vector for instructions embedded in comments or data to influence agent behavior.
- Ingestion points: The skill uses the read_file tool to ingest code surfaces for review (SKILL.md).
- Boundary markers: While the skill specifies a rigid output contract (findings, patch-plan, risk), it does not explicitly instruct the model to ignore potential instructions embedded within the analyzed files.
- Capability inventory: The agent's capabilities are strictly limited to the read_file tool; it does not have access to tools for network communication, file system modification, or command execution, which prevents the realization of high-impact exploitation.
- Sanitization: There is no specific evidence of input sanitization or filtering applied to the content retrieved by the read_file tool.
Audit Metadata