skills/sehoon787/my-claude/ccg/Gen Agent Trust Hub

ccg

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of global NPM packages @openai/codex and @google/gemini-cli. These packages are associated with established organizations (OpenAI and Google).
  • [COMMAND_EXECUTION]: The workflow relies on executing shell commands via the omc ask CLI tool. It passes dynamically generated strings as arguments to these commands, which is the primary mechanism for model orchestration.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted data from external sources and has the following characteristics:
  • Ingestion points: Reads model output artifacts from .omc/artifacts/ask/ (SKILL.md).
  • Boundary markers: None identified; instructions do not specify the use of delimiters or warnings to ignore embedded commands in advisor outputs.
  • Capability inventory: Uses the Bash tool to execute omc ask commands (SKILL.md).
  • Sanitization: No sanitization or validation of the advisor-generated markdown files is performed before synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:43 AM
Security Audit — agent-trust-hub — ccg