opensource-readme-generator
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface.
- Ingestion points:
SKILL.mdinstructs the agent to "Analyze the Project" by looking at files in the current directory (e.g.,ls -R, readingpackage.json,requirements.txt) and gathering project info. - Boundary markers: There are no specific delimiters or instructions provided to the agent to treat local file content as untrusted or to ignore instructions embedded within those files.
- Capability inventory: The skill utilizes directory exploration and the
write_filetool to modify the filesystem. - Sanitization: No sanitization or validation of the ingested file content is performed before it is processed or used to generate the output README.
- DATA_EXPOSURE & EXFILTRATION (SAFE): No sensitive data exposure detected. The
assets/all-star-readme-template.mdfile contains an API key placeholder (ENTER YOUR API) which is a safe and standard practice for templates. - REMOTE_CODE_EXECUTION (SAFE): While the README template includes markdown blocks with shell commands (e.g.,
npm install), these are intended as documentation for the end-user and are not instructions for the agent to execute during the skill's operation.
Audit Metadata