pr-prep
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill has an attack surface where malicious data in a repository could influence agent behavior. 1. Ingestion points: Reads data from
git logandgit diff(SKILL.md, case-study-historical-context.md). 2. Boundary markers: Absent; git outputs are interpolated directly into generated descriptions. 3. Capability inventory: Execution of build/test tools and network-enabled submission viagh pr create. 4. Sanitization: No validation or escaping of external content before processing. - Command Execution (SAFE): The skill uses local subprocesses (
npm,go,pytest) for their intended purpose of validating code before submission. The validation scriptvalidate.shusesevalfor routine environment checks. - Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file access (e.g., SSH keys), or unauthorized network exfiltration patterns were detected.
- Prompt Injection (SAFE): The skill does not contain instructions to bypass agent safety filters or override system-level constraints.
Audit Metadata