omh-report-package

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill incorporates specific calls to a local CLI tool (omh) to record runtime status and export achievement data within SKILL.md. These commands are part of the intended reporting workflow within the platform environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data to generate report packages and outlines. This creates a surface where malicious instructions embedded in the input data could influence the agent's output. 1. Ingestion points: Untrusted data enters the context via user-provided 'supplied facts', 'reporting period', and 'audience' inputs in SKILL.md. 2. Boundary markers: The instructions in SKILL.md do not define any specific delimiters or boundary markers to isolate user-provided inputs from the agent's internal instructions. 3. Capability inventory: The skill calls the omh CLI tool for record and export functions in SKILL.md, but does not specify file-write or network operations. 4. Sanitization: SKILL.md contains no instructions for sanitizing, escaping, or validating external content before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:33 PM
Security Audit — agent-trust-hub — omh-report-package