gh-search-issues
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains purely instructional content and command examples for the official GitHub CLI (
gh). No command execution of arbitrary scripts, network exfiltration, or obfuscation was detected. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data (GitHub issue titles, bodies, and comments) into the agent's context, which could theoretically contain malicious instructions.
- Ingestion points: Output from
gh search issues(SKILL.md). - Boundary markers: Absent in the skill instructions; however, the tool is primarily documented to provide structured JSON output which helps delineate data from instructions.
- Capability inventory: Execution of
gh search issuescommands to retrieve remote repository data. - Sanitization: No specific instructions for sanitizing or escaping the content of retrieved issues before further processing by the agent.
Audit Metadata