felo-x-search

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No prompt injection or instructions to bypass safety guidelines were found in the skill's markdown files.
  • [SAFE]: The skill handles authentication securely using the FELO_API_KEY environment variable.
  • [SAFE]: All network operations are directed to the vendor's official API domain (openapi.felo.ai).
  • [SAFE]: No obfuscation, persistence, or privilege escalation patterns were detected in the source code or instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external sources (X/Twitter) which could contain malicious instructions.
  • Ingestion points: The scripts/run_x_search.mjs script retrieves tweets, user bios, and replies from the X platform via API.
  • Boundary markers: Absent. The retrieved data is output as standard Markdown without explicit delimiters warning the agent that the content is untrusted.
  • Capability inventory: The skill includes network access to the Felo API and outputs formatted text to the console; it does not perform file writes or arbitrary command execution based on the data.
  • Sanitization: Absent. Tweet content and user descriptions are displayed without filtering for potential prompt injection strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 07:07 AM