checking-owasp-compliance
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process files from an external codebase, creating a surface for indirect prompt injection if malicious instructions are embedded in the scanned files.
- Ingestion points: The
scripts/owasp_scan.pyscript recursively traverses the input directory usingrglob("*")and reads file metadata or JSON content. - Boundary markers: There are no specific boundary markers or instructions to ignore embedded commands present in the scripts to delimit untrusted data from the codebase.
- Capability inventory: The skill is granted extensive
Bashexecution privileges (security:*,scan:*,audit:*) and file system tools (Write,Edit), which could be leveraged if an injection attack successfully influences the agent's behavior. - Sanitization: The provided processing script performs basic metadata checks but does not sanitize file content before it is potentially analyzed by the agent.
Audit Metadata