The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external Feishu/Lark documents which are retrieved via the lark-cli docs +fetch command. This creates a surface for indirect prompt injection attacks where an attacker could embed malicious instructions within a document to manipulate the AI's output or trigger unintended tool usage.
Ingestion points: Document content is fetched in SKILL.md (Step 2) using lark-cli docs +fetch.
Boundary markers: The workflow does not specify clear delimiters or instructions for the agent to ignore potentially malicious embedded content during summarization.
Capability inventory: The skill includes capabilities to search the drive (drive files search) and modify or create documents (docs +update, docs +create).
Sanitization: No explicit sanitization or filtering of the document content is described before it is passed to the AI for processing.
[EXTERNAL_DOWNLOADS]: The skill documentation references external configuration and shared logic from the larksuite/cli repository on GitHub. These references target official resources from a well-known service provider.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute several shell commands using the lark-cli binary, including auth login, wiki spaces get_node, docs +fetch, drive files search, and docs +update. These commands are necessary for the skill's stated functionality of document management and summarization.

lark-workflow-doc-summarizer