git-collaboration-master
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The file
scripts/branch_cleanup.jsimports thechild_processmodule (execSync) but does not actually invoke it to execute shell commands; the script's functionality is limited to console logging. - [PROMPT_INJECTION] (LOW): Category 8: Indirect Prompt Injection. The skill is intended to process untrusted data from Git history and pull request templates. 1. Ingestion points: PR descriptions and commit logs as described in
SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill includes a Node.js script environment (scripts/branch_cleanup.js), though it is currently passive. 4. Sanitization: None detected.
Audit Metadata