The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @useclawlink/cli package from the NPM registry. This package is the official tool provided by the skill's author for managing service integrations.
[CREDENTIALS_UNSAFE]: The documentation identifies that authentication tokens are stored locally at ~/.clawlink/credentials.json. This is standard behavior for CLI tools and does not constitute a security risk, as the data remains on the user's local file system.
[PROMPT_INJECTION]: The skill facilitates the processing of user-provided natural language and JSON payloads into Webex API actions, which presents a surface for indirect prompt injection.
Ingestion points: User instructions and JSON input strings passed to the npx @useclawlink/cli command in SKILL.md.
Boundary markers: The skill instructions explicitly mandate that the agent must read data first and request user confirmation before performing any write operations.
Capability inventory: The integration allows reading and updating Webex data (meetings, messages, calls) via the vendor's CLI.
Sanitization: Input is managed by the vendor-provided CLI and the Webex API, with a mandatory human-in-the-loop step for safety.

webex