security-review
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches foundational security playbooks and OWASP-based rules from the Project CodeGuard repository on GitHub (github.com/cosai-oasis/project-codeguard). This is a standard operation for the skill's purpose and uses a well-known service.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted code from target repositories. 1. Ingestion points: Reads all text-based files in the target codebase, including critical configuration and source files (Security_Code_Reviewer_Guidelines.md, Phase 2). 2. Boundary markers: No explicit instructions or delimiters are used to isolate untrusted code from the agent's internal logic. 3. Capability inventory: The skill has the capability to write reports to the local file system (SKILL.md, Output section). 4. Sanitization: No sanitization or filtering of analyzed code is performed before processing.
Audit Metadata