skills/clawlink-hq/skills/box/Gen Agent Trust Hub

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 npx to fetch and execute the @useclawlink/cli package 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 box actions (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
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — box