call-prep

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources to build meeting briefs, creating a potential surface for indirect prompt injection.
  • Ingestion points: Salesforce record descriptions, email threads, Slack messages, and document contents (SKILL.md).
  • Boundary markers: Absent; the skill does not provide instructions to ignore embedded commands.
  • Capability inventory: Salesforce tools (dispatch, dispatch_readonly) and external search tools (SKILL.md).
  • Sanitization: Absent; no sanitization or filtering is performed on retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:39 PM