sprint
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local repository scripts located in .claude/scripts/ and .claude/hooks/, as well as standard development tools like git and gh (GitHub CLI) for branch and pull request management.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted data from GitHub issues. 1. Ingestion points: GitHub issue content extracted by sub-agents in Step 2. 2. Boundary markers: Absent. The sub-agent prompt templates do not utilize delimiters or specific instructions to disregard embedded commands in the issue text. 3. Capability inventory: The skill environment allows for shell command execution, file system writes, and remote repository pushes. 4. Sanitization: Absent. The issue content is used directly to derive implementation tasks for worker agents.
Audit Metadata