google-docs
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands via the
@useclawlink/clitool to interact with Google Docs actions like searching, reading, and creating documents. - [EXTERNAL_DOWNLOADS]: The skill facilitates the download and execution of the
@useclawlink/clipackage from the npm registry, which is a well-known service. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Google Docs, creating an attack surface where instructions embedded in documents could influence agent behavior. 1. Ingestion points: External document content fetched via actions such as
googledocs_get_document_plaintext. 2. Boundary markers: The skill includes a guideline to confirm with the user before performing any write operations. 3. Capability inventory: The skill possesses capabilities for shell command execution and network access through the ClawLink CLI. 4. Sanitization: There is no evidence of automated sanitization or filtering of the retrieved document content in the provided instructions.
Audit Metadata