git-commit-scope-constitution
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/extract_scopes.pyexecutes thegit logcommand viasubprocess.runto retrieve history for analysis. The command is constructed as a list withoutshell=True, which is a safe practice. - [PROMPT_INJECTION]: The skill processes git commit history, creating a surface for indirect prompt injection. Malicious instructions could be embedded in commit messages to influence the agent's reasoning when it drafts the constitution.
- Ingestion points: Commit messages processed in
scripts/extract_scopes.py. - Boundary markers: None.
- Capability inventory: The agent can write to files like
.github/git-scope-constitution.md. - Sanitization: No validation or sanitization is performed on commit message content.
Audit Metadata