felo-web-fetch
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill communicates exclusively with the vendor's official API endpoint at https://openapi.felo.ai to perform its stated function of web content extraction.
- [DATA_EXFILTRATION]: The skill transmits user-provided URLs and optional metadata, such as cookies and custom user-agent strings, to the Felo API. This is the intended functionality of the tool and is performed via standard HTTPS requests to the author's infrastructure.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by retrieving and displaying content from external URLs. 1. Ingestion points: scripts/run_web_fetch.mjs (via the fetch call to the Felo API). 2. Boundary markers: Absent; fetched content is printed directly to stdout. 3. Capability inventory: The skill is limited to making network requests to the vendor API and does not have local file system write access or subprocess execution capabilities (scripts/run_web_fetch.mjs). 4. Sanitization: Absent; the raw content is passed to the agent's context.
Audit Metadata