wp-dependency-security-audit
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze third-party code, lockfiles, and manifests which constitute untrusted data. This creates a vulnerability surface where malicious instructions could be embedded in the files being audited. Ingestion points: Manifests and vendor directories searched via
rg(ripgrep). Boundary markers: The instructions do not specify explicit delimiters or warnings to isolate analyzed content. Capability inventory: Primarily read-only file searching and auditing; no write or unexpected network capabilities. Sanitization: No specific input sanitization is described. - [COMMAND_EXECUTION]: The skill instructs the agent to execute
rg(ripgrep) commands to search for manifests, source maps, and version banners. These commands are localized to the project directory and are standard for the intended audit functionality.
Audit Metadata