unifuncs-reader
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill transmits data to and from the UniFuncs API (api.unifuncs.com) to perform content extraction, which is the primary purpose of the tool.
- [DATA_EXPOSURE]: The skill requires an API key (UNIFUNCS_API_KEY) which it correctly retrieves from environment variables, avoiding hardcoded secrets.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it retrieves and processes unsanitized content from arbitrary external URLs. Instructions embedded in the target web pages could potentially influence the behavior of the AI agent.
- Ingestion points: Remote content fetched from user-provided URLs in
read.py. - Boundary markers: No delimiters or ignore-instructions markers are used when outputting the fetched content.
- Capability inventory: The skill has the capability to execute Python scripts and perform network operations.
- Sanitization: The fetched content is returned directly as markdown or text without filtering for embedded instructions.
Audit Metadata