local-discovery

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill relies on extracting information from external web sources which could contain malicious instructions.
  • Ingestion points: Untrusted data is ingested from various event and venue websites via web_extract and browser_navigate as described in SKILL.md.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are provided to the agent for processing the external content.
  • Capability inventory: The skill instructions in SKILL.md only involve web-based tools (web_search, web_extract, browser_navigate) and do not utilize any sensitive capabilities like file writing or shell access.
  • Sanitization: There is no evidence of sanitization or input validation for the data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:56 AM
Security Audit — agent-trust-hub — local-discovery