dropbox
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 downloads and executes the latest version of the ClawLink CLI from the public NPM registry at runtime. - [COMMAND_EXECUTION]: All Dropbox operations (listing folders, reading files, uploading content) are performed by executing shell commands via the
@useclawlink/clitool. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from an external source (Dropbox) which could contain malicious instructions targeting the agent.
- Ingestion points: Data is retrieved from Dropbox via actions like
dropbox_read_fileanddropbox_search_file_or_folder(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The agent has shell command execution capabilities via the CLI tool (SKILL.md).
- Sanitization: There is no evidence of content sanitization or validation for the data retrieved from Dropbox.
Audit Metadata