owasp-security-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data in the form of source code from external repositories and pull requests, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill description in
SKILL.mdspecifies that it performs reviews across "application repositories, services, libraries, and pull requests." - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded within the code being analyzed.
- Capability inventory: The skill allows for file creation (
poc_<finding_slug>.py) and suggests retrieving upstream OWASP pages, which implies network and filesystem capabilities if the host agent supports them. - Sanitization: There are no instructions for sanitizing or escaping the content of the analyzed code before it is processed by the agent's logic.
Audit Metadata