dub
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npx @useclawlink/cli, which fetches and executes the command-line tool from the NPM registry at runtime. The package is owned by the skill's vendor, clawlink-hq. - [COMMAND_EXECUTION]: The skill relies on shell command execution via the ClawLink CLI to log in, connect to services, and run specific actions against the Dub API.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The agent receives and processes data from the Dub platform via CLI commands like
npx @useclawlink/cli run dubandnpx @useclawlink/cli actions dubin SKILL.md. - Boundary markers: The instructions explicitly state to "confirm with the user before any write," providing a human-in-the-loop checkpoint.
- Capability inventory: The skill has the capability to execute shell commands and read/write to the local filesystem (specifically
~/.clawlink/credentials.json). - Sanitization: The skill does not define specific sanitization or filtering for data retrieved from the external Dub service, relying on the agent's internal safety guardrails.
Audit Metadata