The Agent Skills Directory

[SAFE]: The skill uses established yuque-mcp tools to interact with the Yuque API. All operations, such as listing repositories and reading document content, are consistent with the stated purpose of auditing knowledge base freshness.
[SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or hidden URLs, are present in the skill's instructions or metadata.
[SAFE]: The skill does not contain hardcoded credentials or instructions to exfiltrate data to third-party domains. It follows standard practices by utilizing the pre-configured yuque-mcp server for authentication.
[SAFE]: While the skill ingests external data (document content), it lacks dangerous capabilities like shell execution or file-writing that would enable a successful indirect prompt injection attack.

stale-detector