analytics

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read project-specific context files, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The skill reads files such as .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md from the local directory to gather business context.
  • Boundary markers: The skill provides no specific delimiters or instructions to the agent to disregard potentially malicious commands that might be embedded within these context files.
  • Capability inventory: The skill is primarily instructional, generating tracking plans and code snippets for GA4 and GTM. It does not include built-in capabilities for arbitrary shell execution or network operations.
  • Sanitization: There is no logic provided to sanitize, validate, or filter the content retrieved from the external context files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:34 AM
Security Audit — agent-trust-hub — analytics