pr-code-review
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the presence and execution of
gh(GitHub CLI) andglab(GitLab CLI) to publish review results as comments on the respective platforms. This is the intended primary function of the skill.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the nature of processing untrusted external data. - Ingestion points: The skill ingests data from PR/issue bodies, linked tickets, and repository source code (specifically referenced in the 'Process' section of
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to isolate untrusted PR content from the agent's core instructions.
- Capability inventory: The agent has the capability to execute shell commands (
gh,glab) and read arbitrary files within the repository. - Sanitization: The skill does not mention any sanitization, filtering, or validation of the text ingested from PRs or issues before processing.
Audit Metadata