add-model Audit-Bericht.

Warnungen

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
• The SKILL.md excerpt appears cut off in the middle of the Consumption Matrix; ensure the full matrix is present in the actual file so agents have complete capability-flag guidance.
• The skill accepts a user-supplied docs-url but does not explicitly require validating that it is an official provider domain, which could expose the agent to typosquatted or malicious documentation sources.
• The workflow says to run lint but does not explicitly mention running relevant tests or checking for generated docs updates that may be required by the repo's CI.
• This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
• 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

Methode

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.