prefer-make
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill creates an attack surface by instructing the agent to read and follow instructions found in a project Makefile. 1. Ingestion points: Makefile. 2. Boundary markers: Absent. 3. Capability inventory: Execution of arbitrary shell commands via make targets. 4. Sanitization: Absent.
- [Prompt Injection] (SAFE): No direct behavior override or safety bypass patterns were identified in the skill instructions.
- [Data Exposure] (SAFE): No hardcoded secrets or access to sensitive local files (e.g., SSH keys, environment variables) were found.
- [Command Execution] (SAFE): The execution of make commands is necessary for the skill's primary function and does not involve elevated privileges or suspicious download-to-bash patterns.
Audit Metadata