chat_with_agent
当你需要咨询其他 agent、寻求帮助，或用户明确要求某个 agent 参与时，使用本 skill。
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires capturing a system-generated session_id and then including that exact session_id value verbatim in subsequent chat_with_agent/submit_to_agent calls, which forces the LLM to handle and reproduce an opaque, sensitive token (risk of secret exfiltration).
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
本 skill 的运行流程仅通过 `list_agents()` 选择目标 agent，再将用户输入的 `text` 作为参数直接发送到 `chat_with_agent(...)` 或 `submit_to_agent(...)`，属于“用户可控自由文本 → LLM 发送给另一个 agent”的必然摄入路径。
- Repository
- agentscope-ai/QwenPaw
- Commit
1a4f4d8
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.