search-campaign-audit

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: Analysis of the skill reveals no malicious patterns, unauthorized data access, or suspicious network activity. The tools and external links provided are consistent with the verified vendor (Cogny AI).\n- [PROMPT_INJECTION]: The skill ingests external search term data from Google Ads. While this constitutes a potential indirect prompt injection surface, the risk is minimal as the instructions are restricted to analytical reporting and do not involve executing untrusted content.\n
  • Ingestion points: search_term_view data retrieved via GAQL.\n
  • Boundary markers: None.\n
  • Capability inventory: WebFetch, WebSearch, mcp__cogny__create_finding.\n
  • Sanitization: Not explicitly implemented for search term strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 11:32 AM
Security Audit — agent-trust-hub — search-campaign-audit