The Agent Skills Directory

[SAFE]: The skill facilitates communication with the Feishu platform using a specialized CLI tool (feishu-cli). All operations described (sending, replying, forwarding) are consistent with its stated purpose of message management and follow standard integration patterns.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute feishu-cli commands. This is the intended and necessary mechanism for the skill's functionality.
[EXTERNAL_DOWNLOADS]: The documentation references an external GitHub repository (github.com/riba2534/feishu-cli) for installation instructions. Since the repository belongs to the skill's author, it is considered a legitimate vendor resource.
[DATA_EXFILTRATION]: While the skill transmits data to the Feishu platform, these operations are restricted to the messaging functionality requested by the user. No evidence was found of unauthorized data transmission or exfiltration of sensitive local information.
[SAFE]: Indirect Prompt Injection Surface: The skill can ingest untrusted data when fetching message content or thread history using feishu-cli msg get or feishu-cli msg thread-messages. While this creates a potential attack surface, it is a necessary part of the skill's functionality for managing conversations.
Ingestion points: feishu-cli msg get, feishu-cli msg mget, feishu-cli msg thread-messages in SKILL.md
Boundary markers: Absent
Capability inventory: Bash, Write in SKILL.md
Sanitization: Absent

feishu-cli-msg