code-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted source code or pull request data provided by users. This creates a potential attack surface where malicious instructions could be embedded within the processed code to influence the agent's output.
- Ingestion points: Processes user-supplied source code in various languages (JavaScript, Go, Java, Python, etc.) as part of the review instructions in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or explicit 'ignore instructions' warnings when processing the input code.
- Capability inventory: The skill consists entirely of markdown files and contains no automated scripts, shell command executions, network operations, or file system write capabilities within its own distribution.
- Sanitization: There are no explicit instructions for the agent to sanitize or filter the input data before analysis.
Audit Metadata