The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of shell commands including curl for API interactions, python3 -c for JSON processing, and npx for package execution during setup.
[DATA_EXFILTRATION]: The skill is designed to transmit local data, specifically Markdown files, to Feishu's external servers (open.feishu.cn) through the md2feishu.sh script.
[CREDENTIALS_UNSAFE]: The feishu-mcp-setup.js script is designed to collect and write Feishu API credentials (app_id and app_secret) into the global ~/.claude.json configuration file in plain text.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from external sources.
Ingestion points: Functions in feishu_api.py such as get_bitable_records, get_doc, and list_chats read data from the Feishu platform.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when processing external data.
Capability inventory: The skill has access to powerful tools including Bash, Write, and Edit which could be abused if malicious instructions are ingested.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from Feishu before it is processed by the agent.

feishu-automation