check-bun
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill utilizes standard system utilities such as grep, ls, and test to perform its audit. These operations are diagnostic, read-only, and confined to the project directory.
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it processes untrusted data from local project files. 1. Ingestion points: package.json, vercel.json, app.json, netlify.toml, and source files in src/ (processed in SKILL.md). 2. Boundary markers: Absent; file content is piped directly to grep. 3. Capability inventory: Restricted to read-only shell diagnostics; no network or file-write operations. 4. Sanitization: Absent.
Audit Metadata