crm-hygiene

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by directing the agent to ingest and analyze untrusted external data from CRM exports.
  • Ingestion points: The 'For Data Audit' section and example scenarios in SKILL.md where users are prompted to paste CRM data exports for analysis.
  • Boundary markers: The instructions do not define delimiters or provide specific prompts to ignore embedded instructions within the processed data.
  • Capability inventory: No high-risk capabilities were detected; the skill does not utilize network access, file system writes, or command execution tools.
  • Sanitization: The skill does not implement validation, escaping, or sanitization of the external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:26 PM
Security Audit — agent-trust-hub — crm-hygiene