Skills
skills/sisodiabhumca/agent-skills/crm-opportunity-summarizer/Gen Agent Trust Hub

crm-opportunity-summarizer

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior or security vulnerabilities were detected in the skill instructions or code. The skill correctly utilizes environment variables for sensitive API tokens.
  • [PROMPT_INJECTION]: The skill processes data from external CRM systems and CSV files, which constitutes an indirect prompt injection surface.
  • Ingestion points: summarize.py (via load_csv, fetch_salesforce, and fetch_hubspot functions).
  • Boundary markers: No delimiters or specific instructions are used to separate ingested data from agent instructions.
  • Capability inventory: The skill can write summaries to the local file system or standard output via summarize.py.
  • Sanitization: No data sanitization or instruction-filtering is performed on the ingested CRM data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 04:06 PM
Security Audit — agent-trust-hub — crm-opportunity-summarizer