agent-issue-tracker
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool and shell hooks (preandpost) to interact with the GitHub CLI (gh). These commands check authentication status and manage issues within the user's repositories (e.g.,ruv-FANN). This execution is a primary function of the skill. - [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues and comments, creating a surface for indirect prompt injection.
- Ingestion points: Data retrieved from external repositories via
mcp__github__list_issues,mcp__github__get_issue, andmcp__github__search_issuesas described in the Usage Patterns. - Boundary markers: Not explicitly defined; the skill interpolates external content directly into task descriptions and comments without visible delimiters.
- Capability inventory: The agent possesses
Bash,TodoWrite,Read, andWritetools, which could potentially be triggered by instructions embedded in external content. - Sanitization: No explicit content validation or sanitization logic is present in the skill instructions.
Audit Metadata