gtm-plays-11

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @coldiq/mcp package using npx. This is a vendor-owned resource provided by the author to support the skill's features.
  • [PROMPT_INJECTION]: The skill is designed to ingest data from external sources such as G2 reviews and social media profiles, which introduces an indirect prompt injection surface.
  • Ingestion points: Processes external inputs from reviews and LinkedIn profile data in Play #2 and Play #8.
  • Boundary markers: Templates interpolate data directly into message bodies without specific isolation markers or safety instructions.
  • Capability inventory: Uses the mcp__coldiq__* tool suite for data enrichment and automated searches.
  • Sanitization: No explicit sanitization or validation of external content is defined in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — gtm-plays-11