readme-generator
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICAL
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill ingests untrusted metadata from local project files (e.g., package.json, Cargo.toml) to populate templates. While this creates an ingestion surface, the risk is minimal as the data is used strictly for documentation generation without exposure to high-privilege tools. Ingestion points: package.json, Cargo.toml, pyproject.toml, setup.py, README.md; Boundary markers: Absent; Capability inventory: Shell-based metadata extraction (cat, grep, jq) and text formatting; Sanitization: None.
- [Command Execution] (SAFE): Shell commands are used solely for non-destructive inspection of project structure (ls, grep, cat, jq). There is no use of arbitrary execution primitives like eval, exec, or suspicious network piping.
- [Automated Scan Evaluation] (SAFE): The security alert flagging 'main.rs' as a malicious URL is a false positive. No file named 'main.rs' is included in the skill package; the term appears only in instructions for detecting Rust project types, which is a standard and safe operation.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata