requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a set of shell commands using
grep,git, andgh(GitHub CLI) to verify pull request attributes. These commands are intended to be executed by the agent to automate checks for description completeness, diff size, and CI status. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests untrusted data from pull request titles, descriptions, and source code into shell command arguments. Ingestion points: Pull request descriptions (via
<pr_description>), titles (via<pr_title>), and changed files (via<changed_files>). Boundary markers: Absent. Capability inventory: Execution ofgrep,git, andghsubprocesses. Sanitization: Absent. This configuration could allow a malicious pull request to influence the verification logic or execute unintended commands if the agent does not properly sanitize these inputs before interpolation.
Audit Metadata