The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute local CLI commands via the Bash tool to interact with the Feishu API.\n
Evidence: Commands such as feishu-cli auth check, feishu-cli auth login, and various search subcommands are utilized.\n
Context: These commands are used for legitimate session management and data retrieval according to the skill's primary purpose.\n- [EXTERNAL_DOWNLOADS]: The skill references an external repository for the installation of its required CLI tool.\n
Evidence: Links to github.com/riba2534/feishu-cli for installation instructions.\n
Context: The resource belongs to the skill's author and is provided for legitimate functional dependency.\n- [PROMPT_INJECTION]: The skill processes external data retrieved from search results, creating an indirect prompt injection surface.\n
Ingestion points: Search result content from Feishu documents, messages, and apps entering the agent context via feishu-cli output (SKILL.md).\n
Boundary markers: No specific delimiters or warnings against embedded instructions are provided in the command examples.\n
Capability inventory: The skill allows the use of the Bash tool for command execution.\n
Sanitization: No explicit sanitization or validation of the retrieved content is described in the skill instructions.\n
Context: This is a standard surface for search-based functionality and is considered an operational risk inherent to the tool's intended use.\n- [SAFE]: No signs of obfuscation, unauthorized data exfiltration, or persistence mechanisms were detected within the skill content.

feishu-cli-search