github-review-issue
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the GitHub CLI (
gh) to retrieve issue metadata, descriptions, and comments. This is a legitimate use of the tool for the skill's stated productivity purpose. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it incorporates untrusted data from GitHub issues into the agent's context for analysis.
- Ingestion points: External data is retrieved via the
gh issue viewcommand inSKILL.md(Step 2). - Boundary markers: There are no explicit delimiters (e.g., XML tags or Markdown blocks) or specific instructions to the agent to disregard any commands found within the fetched issue content.
- Capability inventory: The skill's primary capability is executing the
ghtool to view repository information. - Sanitization: The skill does not perform any validation or sanitization of the issue body or comments before passing them to the agent for summarization.
Audit Metadata