skills/hungv47/comms-skills/imc-plan/Gen Agent Trust Hub

imc-plan

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed entirely of markdown instructions for an LLM and does not contain any executable code, scripts (Python, Node.js, Shell), or system commands.
  • [SAFE]: Data access is limited to reading local marketing research artifacts (e.g., .agents/mkt/icp-research.md) and generating a strategic plan document. No evidence of unauthorized file access, credential harvesting, or network operations was found.
  • [SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or hidden text patterns, are present in any of the analyzed files.
  • [SAFE]: The skill does not attempt to override agent safety protocols or perform prompt injection. All instructions are focused on the stated marketing planning purpose.
  • [SAFE]: The multi-agent orchestration logic is transparent and sequential, relying on clear role definitions and boundaries for each sub-agent (e.g., Pillar Agent, Angle Agent).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 10:07 AM