blueprint-derive-rules
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability where malicious commit messages could be codified into project rules. Ingestion points: Git history processed in Step 3. Boundary markers: None present. Capability inventory: Bash, Write, and Task tools. Sanitization: No sanitization of commit content before rule generation.
- [COMMAND_EXECUTION]: The skill executes shell commands using user-supplied parameters like '--scope' and '--since', which could allow for command injection if inputs are not properly sanitized.
Audit Metadata