The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to download and install the feishu-cli tool from the author's public GitHub repository (github.com/riba2534/feishu-cli).
[COMMAND_EXECUTION]: Uses the Bash tool to execute feishu-cli commands for document export (doc export, wiki export), node retrieval (wiki nodes), and authentication management (auth login, auth status).
[DATA_EXFILTRATION]: The skill reads sensitive authentication tokens from the local file system at ~/.feishu-cli/token.json and accesses the FEISHU_USER_ACCESS_TOKEN environment variable to authenticate API requests.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill reads untrusted content from external Feishu cloud documents and wiki pages, as well as metadata from knowledge bases (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested document content provided in the skill instructions.
Capability inventory: The agent has access to Bash, Read, and Grep tools, allowing it to execute system commands and read files in the /tmp directory where document content is stored.
Sanitization: No evidence of sanitization or filtering of the external document content exists before it is processed by the agent.

feishu-cli-read