felo-web-fetch
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch content from external URLs and provide it to the agent, which is a standard surface for indirect prompt injection attacks.
- Ingestion points: The
run_web_fetch.mjsscript retrieves data from external webpages via the Felo Web Extract API. - Boundary markers: The script outputs the raw extracted content (markdown, HTML, or text) without surrounding it with delimiters or providing instructions to the agent to treat the content as untrusted data.
- Capability inventory: The skill performs network operations via the
fetchAPI to interact with the vendor's extraction service. - Sanitization: There is no evidence of filtering or sanitizing the fetched content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The documentation includes instructions for installing the skill and its dependencies from official vendor sources, including the NPM registry and the vendor's GitHub repository.
Audit Metadata