omh-support-operations

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill demonstrates secure design by establishing clear boundaries for agent capabilities. It explicitly forbids performing high-risk actions such as account mutations, message delivery, or financial transactions (refunds), limiting the output to drafts and recommendations.
  • [COMMAND_EXECUTION]: The skill utilizes a platform-specific command omh runtime record for operational logging. This command is used to track the lifecycle of the support workflow and does not involve user-controlled parameters or sensitive file access.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest untrusted customer support cases, which is a known attack surface for indirect prompt injection. The risk is mitigated by explicit instructions to separate facts from recommendations and the enforcement of a non-execution policy for downstream tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:34 PM
Security Audit — agent-trust-hub — omh-support-operations