The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx -y mcporter to download and execute the 'mcporter' package from the npm registry to facilitate communication with Lark MCP server streams.
[INDIRECT_PROMPT_INJECTION]: The skill manages and processes untrusted data from external sources including chats, emails, and cloud documents, which is a known attack surface for indirect prompt injection. * Ingestion points: The skill reads content from Lark/FeiShu chat, mail, and document streams as described in SKILL.md. * Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore instructions embedded within the retrieved Lark content. * Capability inventory: The skill has the capability to perform API actions such as sending messages or modifying documents using the mcporter call command based on processed content. * Sanitization: No sanitization or validation logic is specified for the external data before it is presented to the agent.

mcp-lark