crm-data-governance

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically CRM metadata and field exports, which could potentially contain malicious instructions.
  • Ingestion points: The skill instructs the agent to export or query field lists from CRM objects and build dictionaries based on these external exports in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to the agent to disregard instructions embedded within the ingested data.
  • Capability inventory: The skill coordinates with other RevOps tools (e.g., mbfinotti/revops-skills@sales-pipeline-hygiene) which may perform actions based on the governance rules derived from this data.
  • Sanitization: There are no explicit requirements for the agent to sanitize or validate the content of the field exports before processing them into the dictionary.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:17 PM
Security Audit — agent-trust-hub — crm-data-governance