justfile-expert
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill documents the use of Justfiles which introduces an indirect prompt injection surface when the agent interacts with external project files. Ingestion points: User-provided Justfiles and .env files read using Grep or Read tools. Boundary markers: No delimiters or ignore instructions for external data are suggested. Capability inventory: Use of Bash and BashOutput tools allows for arbitrary command execution on the host. Sanitization: The skill does not provide instructions for sanitizing or validating external content before processing.
- [EXTERNAL_DOWNLOADS]: Mentions installation procedures for just-mcp using standard package managers such as npx, uvx, and cargo, which are trusted sources.
- [SAFE]: No malicious obfuscation, persistence mechanisms, or data exfiltration patterns were detected in the skill files.
Audit Metadata