setup-issue-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git remote -vandgit statusto identify the repository's origin and current state, which is necessary for proposing issue tracker locations. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files to inform its configuration logic, presenting a surface for indirect prompt injection if those files contain malicious instructions. Ingestion points:
docs/agents/issue-tracker.md,AGENTS.md, and output fromgitcommands. Boundary markers: The skill does not use explicit delimiters to isolate ingested content within the prompt context. Capability inventory: File system write access and local shell command execution (git). Sanitization: The skill does not perform input sanitization but mitigates risk by requiring explicit user confirmation of all proposed file changes and diffs.
Audit Metadata