felo-x-search
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches X (Twitter) data from the vendor's API at
https://openapi.felo.ai. This is a documented functional requirement for the skill's operation.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from X (Twitter), such as tweet text, user biographies, and replies, which could contain instructions designed to influence the agent's behavior.\n - Ingestion points: Data is retrieved from various endpoints under
https://openapi.felo.ai/v2/x/within thescripts/run_x_search.mjsscript and viacurlcommands.\n - Boundary markers: The retrieved content is formatted using standard Markdown but lacks specific delimiters or instructions to the agent to disregard potentially malicious commands embedded in the data.\n
- Capability inventory: The skill performs network requests to the vendor's API and outputs retrieved data to the agent's context.\n
- Sanitization: No sanitization or filtering logic was identified to prevent the agent from interpreting social media content as valid instructions.
Audit Metadata