gtm-competitive-intel

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate market research and document generation as described in its metadata.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the WebSearch tool to gather information from public websites such as competitor homepages and review platforms.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from the web. 1. Ingestion points: External web content retrieved via WebSearch in sub-agent tasks. 2. Boundary markers: Absent in sub-agent prompts. 3. Capability inventory: The skill can Read, Glob, Grep, and Write to the local filesystem, and perform WebSearch. 4. Sanitization: No explicit sanitization of web content is performed before synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:36 AM