box
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto fetch and execute the@useclawlink/clipackage from the npm registry. This is the primary mechanism for interacting with the ClawLink service and Box API. The package is provided by the skill's author (clawlink-hq). - [COMMAND_EXECUTION]: The skill relies on shell commands to perform all actions, including logging in, connecting accounts, and executing Box-specific operations like adding shared links or managing users. It explicitly manages local credentials at
~/.clawlink/credentials.json. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads data (file content, metadata, classifications) from an external source (Box). Maliciously crafted content within Box files could attempt to influence agent behavior.
- Ingestion points: Box file data and metadata retrieved via
run boxactions (SKILL.md). - Boundary markers: Not present.
- Capability inventory: Shell command execution via
npx @useclawlink/cli(SKILL.md). - Sanitization: None specified in the instructions.
Audit Metadata