securite-developpement
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves analyzing user-provided source code, configuration files, and infrastructure scripts. This introduces a potential surface for indirect prompt injection, where malicious instructions embedded in the audited files could attempt to manipulate the agent's findings or reporting behavior. The skill includes instructions to validate non-conformities against real code to mitigate this risk.
- Ingestion points: User project files (code, config, CI/CD pipelines) analyzed during the audit workflow defined in
SKILL.md. - Boundary markers: No explicit markers or delimiters are instructed for the agent to wrap analyzed code or ignore embedded instructions.
- Capability inventory: The agent reads local project files and writes audit reports to the
audits/directory on the filesystem. - Sanitization: No explicit sanitization or filtering of the content being audited is defined in the instructions.
Audit Metadata