greenfield-pearl-tracker

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill handles untrusted data from external CRM and call tracking services, which creates a vulnerability surface for indirect prompt injection.
  • Ingestion points: External data is ingested through hubspot_search_deals, clari_search_calls, and clari_get_call_summary tool calls in SKILL.md.
  • Boundary markers: Absent. The instructions do not provide delimiters or directives to the agent to ignore potentially malicious instructions embedded in the call transcripts or deal notes.
  • Capability inventory: The skill is restricted to reading sales data and searching internal product knowledge; no capabilities for shell execution (exec/eval), local file system writes, or outbound network requests to unknown domains were detected.
  • Sanitization: Absent. There is no evidence of data sanitization or validation for the content retrieved from the integrated sales tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 04:24 PM
Security Audit — agent-trust-hub — greenfield-pearl-tracker