competitive-landscape

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources including search engine results (get_serp_results) and user-generated business questions (get_google_business_questions).
  • Ingestion points: Data is pulled through tool outputs into the agent's context during the workflow steps.
  • Boundary markers: There are no explicit instructions to the agent to treat external content as data only or to ignore embedded instructions.
  • Capability inventory: The skill only generates a report (synthesis) and does not utilize file system writes, shell commands, or network requests outside the provided toolset.
  • Sanitization: No explicit sanitization of tool outputs is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:16 PM
Security Audit — agent-trust-hub — competitive-landscape