The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the public npm registry.
[COMMAND_EXECUTION]: Shell commands are used to perform login, connect to Recall.ai, and run specific actions like creating bots or managing calendars.
[CREDENTIALS_UNSAFE]: The documentation identifies that authentication credentials are saved locally in the ~/.clawlink/credentials.json file. While this exposes the storage location, it is presented as standard operational information for the tool.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external meeting platforms, including transcripts and recording metadata.
Ingestion points: Data is ingested via the npx @useclawlink/cli run recallai command which fetches information from Recall.ai and external meeting platforms (Zoom, Google Meet, etc.).
Boundary markers: No explicit delimiting or instructions to ignore embedded commands were found in the skill instructions.
Capability inventory: The skill has the ability to execute shell commands and interact with the filesystem (storing credentials).
Sanitization: There is no evidence of sanitization or filtering applied to the data retrieved from external meeting platforms.

recallai