monday
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the '@useclawlink/cli' package from the NPM registry and connects to the vendor domain 'claw-link.dev'.
- [COMMAND_EXECUTION]: The agent performs actions by executing shell commands via the 'npx @useclawlink/cli' utility.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Monday.com environments, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is ingested from Monday boards, items, and updates through the 'actions', 'describe', and 'run' commands.
- Boundary markers: The instructions explicitly require the agent to 'confirm with the user before any write'.
- Capability inventory: The skill has shell command execution and network communication capabilities through the vendor CLI.
- Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external Monday boards within the skill instructions.
Audit Metadata