call-prep

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected. The skill's functionality is consistent with its documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from potentially untrusted external sources (email, web search results, internal chat) which could contain adversarial instructions.
  • Ingestion points: Data enters the context via CRM queries, email thread searches, internal chat logs, and automated web research results.
  • Boundary markers: The execution flow does not define explicit delimiters or instructions to the model to ignore potential instructions embedded within the ingested data during the synthesis phase.
  • Capability inventory: The skill uses standard platform tools (Read, Glob, Grep) and focuses on generating a text-based prep brief.
  • Sanitization: There is no mention of sanitizing or filtering external content before it is processed for brief generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:49 AM
Security Audit — agent-trust-hub — call-prep