security-auditor
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is comprised solely of markdown instructions and metadata. It does not include any executable scripts, shell commands, or external dependencies. No patterns of data exfiltration, privilege escalation, or persistence were found.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of auditing external systems and documentation.
- Ingestion points: Architecture reviews, SDLC security controls, and CI/CD configuration files described in the instructions.
- Boundary markers: The instructions do not explicitly require the agent to use delimiters or ignore instructions within the audited data.
- Capability inventory: The skill lists a wide range of security testing capabilities (SAST, DAST, etc.) and instructs the agent to perform targeted scans using platform-provided tools.
- Sanitization: There are no instructions for sanitizing or filtering content from audited files before processing them. The risk is mitigated by the persona's explicit instructions to protect sensitive data and operate within an authorized scope.
Audit Metadata