gtm-lead-scoring

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted lead facts and labels, which represents an indirect prompt injection surface.
  • Ingestion points: User-supplied lead facts and persona labels processed in SKILL.md.
  • Boundary markers: None defined for the interpolation of untrusted lead facts.
  • Capability inventory: The skill is restricted to reading persona files from the ~/.gtm/ directory and is explicitly barred from network access or system changes.
  • Sanitization: Instructions in references/context.md direct the agent to filter out credentials, tokens, and session identifiers from input data.
  • [NO_CODE]: The skill consists entirely of markdown instructions and references, containing no executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 03:45 PM
Security Audit — agent-trust-hub — gtm-lead-scoring