omh-meeting-brief

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user data to generate meeting artifacts, which could allow maliciously crafted input to influence agent output.\n
  • Ingestion points: The skill ingests external data for meeting goal, audience, known context, and decision topics (found in SKILL.md).\n
  • Boundary markers: There are no specific delimiters or instructional guardrails defined to separate user-provided meeting context from the skill's logic.\n
  • Capability inventory: The skill interacts with the local file system (referencing omh-routing/references/skill-common-rail.md) and references the omh CLI tool for runtime recording.\n
  • Sanitization: The instructions do not specify any validation or sanitization routines for the ingested meeting details.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:34 PM
Security Audit — agent-trust-hub — omh-meeting-brief