oh-join
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the GitHub CLI (gh) to view issues, list PRs, merge PRs, and update issue bodies. These actions are performed using variables derived from the target issue provided by the user.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and parses untrusted data from GitHub issues and PRs.\n
- Ingestion points: Fetches issue and PR data using
gh issue view,gh pr list, andgh pr viewcommands (SKILL.md).\n - Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are defined for the parsed content.\n
- Capability inventory: The skill has the capability to merge PRs, close issues, and edit issue bodies (SKILL.md).\n
- Sanitization: No explicit sanitization or validation of the ingested strings is performed prior to parsing or interpolation.\n
- Mitigation: The risk is mitigated by a mandatory requirement for an explicit approval from a separate reviewer for the exact final commit before any merge operation can proceed.
Audit Metadata