omh-prompt-import-readiness

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to import prompt files from external sources such as Claude Code and Codex, which creates a surface for indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: Processes external prompt folders and directory-based prompt imports as specified in SKILL.md.
  • Boundary markers: The skill explicitly defines 'prepared-vs-observed' boundaries and safety rules to prevent unverified execution.
  • Capability inventory: Involves prompt mutation, dry-run execution, and slash-command registration.
  • Sanitization: The workflow includes specific recovery notes requiring a security-safety-review for suspicious prompt content or potential injection risks.
  • [DYNAMIC_EXECUTION]: The skill utilizes dynamic argument interpolation to map user inputs to imported slash commands.
  • Evidence: References to $ARGUMENTS mapping, $1-$9 argument syntax, and {{args}} placeholders in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:34 PM
Security Audit — agent-trust-hub — omh-prompt-import-readiness