NYC

leads-researcher

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. * Ingestion points: The skill workflows involve reading and processing content from external company websites, job postings, and news articles as described in references/full-guide.md. * Boundary markers: There are no explicit instructions or delimiters defined to isolate untrusted external content from the agent's internal instructions. * Capability inventory: The skill is intended to perform network requests (fetch) and process the resulting data. * Sanitization: There is no evidence of sanitization or filtering applied to external data before processing.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references legitimate B2B data providers (Clearbit, Hunter.io, Apollo.io) and uses standard API practices. Network operations are consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:18 PM