readme-generator
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes potentially untrusted project files such as package.json, pyproject.toml, and source code docstrings to extract metadata and usage examples. This provides an opportunity for an attacker to embed malicious instructions within these files to influence the agent's behavior during the drafting process.
- Ingestion points: Project configuration files (package.json, pyproject.toml, Cargo.toml, setup.py), existing README.md files, and source code entry points (docstrings).
- Boundary markers: The workflow lacks explicit delimiters or instructions for the agent to treat data from these files as passive text or to ignore embedded instructions.
- Capability inventory: The skill utilizes file discovery (Glob), file reading (Read), and file writing capabilities to create or update README files.
- Sanitization: No explicit sanitization, validation, or filtering of the ingested file content is performed before processing.
Audit Metadata