account-context

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill accesses data through several ingestion points including email, chat history, and meeting transcripts (SKILL.md), which are external and potentially untrusted.
  • Boundary Markers: The instructions include clear boundary markers, directing the agent to treat external content as data only and to report any instruction-like text rather than acting on it.
  • Capability Inventory: The skill has the capability to read CRM and documentation data and post messages to internal chat channels.
  • Sanitization and Review: The skill mitigates risks by preventing the rendering of external links and by requiring explicit human review for any action suggested by the content of the untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:06 PM
Security Audit — agent-trust-hub — account-context