company-radar Informe de auditoría.

Advertencias

• 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
• Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
• No explicit prompt-injection safety guidance: the skill directs agents to ingest web and social media content, which is untrusted, but does not instruct the agent to treat that content as data rather than instructions.
• The skill depends on multiple external opendirectory micro-skills and API keys; if those skills are not installed or platforms are inaccessible, some channels may not work as described.
• Twitter/X data collection is referenced through a skill, but API access and scraping reliability are not addressed, which could cause incomplete signal collection in practice.
• Financial research output is not financial advice; require human review before any live investment decision.
• 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

Método

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.