felo-x-search
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill's source code and configuration files reveals no security violations. The script
scripts/run_x_search.mjscommunicates exclusively with the documented Felo API endpoint (openapi.felo.ai) and handles authentication using standard environment variable patterns. No persistence mechanisms, privilege escalation attempts, or suspicious network operations were detected.\n- [PROMPT_INJECTION]: The skill possesses an inherent surface for indirect prompt injection due to its primary function of retrieving untrusted content from X (Twitter).\n - Ingestion points: External data is ingested via API calls in
scripts/run_x_search.mjs.\n - Boundary markers: Not present; the retrieved tweet and user content are formatted into Markdown headers and lists without specific delimiters to isolate potential instructions.\n
- Capability inventory: The skill provides network access and script execution capabilities to the agent.\n
- Sanitization: None; the skill displays raw content (bios, tweets) which may contain adversarial text designed to influence agent behavior.
Audit Metadata