analyze-issue
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the GitHub CLI (
gh) andgitto fetch issue details and repository information. These are legitimate operations required for the skill's functionality as described in SKILL.md.- [PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues (titles, bodies, and comments), creating a surface for indirect prompt injection attacks. - Ingestion points: External content fetched from GitHub issues in SKILL.md (Step 1).
- Boundary markers: Absent; the agent is not instructed to treat issue content as untrusted or separate it from its instructions.
- Capability inventory: Reads local project files (Step 2) and executes shell commands (
gh,git). - Sanitization: No validation or sanitization is performed on the data retrieved from GitHub.
Audit Metadata