bilt

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill makes network requests to api.biltrewards.com to retrieve travel information. This activity is restricted to public data and is necessary for the skill's functionality.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external content from the Bilt API.
  • Ingestion points: External API responses are ingested through curl commands in SKILL.md.
  • Boundary markers: No delimiters are used to differentiate external data from the agent's internal logic.
  • Capability inventory: The skill uses the Bash tool to execute curl and jq commands.
  • Sanitization: There is no explicit sanitization of the data retrieved from the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 11:13 AM
Security Audit — agent-trust-hub — bilt