auto-quality
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill triggers automatically after every feature completion and is authorized to perform silent fixes. This creates an attack surface where untrusted data can influence the agent's actions.
- Ingestion points: The feature_complete event (SKILL.md).
- Boundary markers: Absent; no delimiters are defined to separate the code being checked from the instructions for fixing it.
- Capability inventory: Explicitly authorized to fix issues, implying file-write or code-modification permissions.
- Sanitization: Absent; no validation or sanitization of the input feature code is specified before the fixing process begins.
Audit Metadata