qe-security-testing
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides legitimate instructional content and code templates for security professionals to identify common vulnerabilities like SQL injection, XSS, and broken access control.\n- [EXTERNAL_DOWNLOADS]: The skill references established security tools and container images (e.g., OWASP ZAP, Snyk, and TruffleHog) within its examples. These tools are from well-known technology organizations and represent standard security industry practice.\n- [INDIRECT_PROMPT_INJECTION]: The skill's intended use case involves the ingestion and analysis of external data from security scanning tools and API responses, creating an attack surface for indirect prompt injection.\n
- Ingestion points: Test output from SAST/DAST tools and raw HTTP responses from testing targets (SKILL.md).\n
- Boundary markers: The instructional text does not specify the use of delimiters or warnings to ignore embedded instructions in external data.\n
- Capability inventory: The skill uses network testing tools (fetch) and executes command-line security utilities (npm audit, git-secrets).\n
- Sanitization: While the skill demonstrates how to test for sanitization on target systems, it does not explicitly define sanitization protocols for the agent's own internal processing of that data.
Audit Metadata