review-code
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze untrusted source code from various sources, which could potentially contain malicious instructions intended to mislead or control the agent's behavior during the review process.
- Ingestion points: The skill reads local files, output from
git diff, and content from GitHub Pull Requests via theghCLI. - Boundary markers: There are no explicit instructions to use delimiters or ignore markers when processing the target code content.
- Capability inventory: The skill utilizes file reading,
gitcommand execution, and theghCLI. It includes a safety constraint to only report findings and not modify code unless explicitly requested by the user. - Sanitization: The skill does not include steps to sanitize or escape the content of the code being reviewed before it enters the agent's context.
- [COMMAND_EXECUTION]: The skill requires the use of shell commands such as
gitand the GitHub CLI (gh) to retrieve the code and metadata for review. These are standard tools used for their intended purpose in a developer-focused skill.
Audit Metadata