oma-image Laporan audit.

Peringatan

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• Financial research output is not financial advice; require human review before any live investment decision
• The skill invokes external CLIs and APIs with user-supplied prompts; there is no explicit guardrail in the provided SKILL.md text about treating prompt content as untrusted data to prevent prompt-injection from propagated instructions.
• SKILL.md excerpt appears truncated at 'Expected inputs', so some agent-facing sections may be incomplete in the submitted source even though the accompanying resource files are thorough.
• Dependence on external binaries (`codex`, `agy`, `oma`) and OAuth/API authentication means environment-specific setup is required; this is documented but could be clearer in the main SKILL.md.
• Financial research output is not financial advice; require human review before any live investment decision.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• Dependency/runtime risk: command execution surface, credential or environment access
• Permission surface: secrets or environment access, shell or command execution

Metode

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.