google-super
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @useclawlink/cli package from the npm registry using the npx command during both setup and runtime.
- [COMMAND_EXECUTION]: Instructions guide the agent to perform shell commands to log in, connect accounts, and execute actions within the Google Super environment.
- [CREDENTIALS_UNSAFE]: The skill documents the storage of authentication credentials at ~/.clawlink/credentials.json, which is the default directory for the vendor's CLI tool.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: User natural language requests are passed directly to the actions command of the CLI in SKILL.md.
- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the provided examples.
- Capability inventory: The agent has the ability to execute shell commands and access the network through the CLI.
- Sanitization: The skill does not perform its own sanitization, relying instead on the internal logic of the @useclawlink/cli tool.
Audit Metadata