Skills
Navigate
skills/cawcut/skill/cawcut-app-run/Gen Agent Trust Hub

cawcut-app-run

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute cawcut CLI commands for listing, describing, and running applications.
  • [COMMAND_EXECUTION]: Utilizes system utilities including sips and ffmpeg for local image and video processing (compression and resizing) when user-provided files exceed platform limits.
  • [EXTERNAL_DOWNLOADS]: Facilitates the installation of the @ubnt/cawcut package from the NPM registry and performs CLI updates via the cawcut upgrade command.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists because the skill ingests and processes application names and descriptions from the remote CawCut app catalog.
  • Ingestion points: Data enters the context via cawcut app list --json and cawcut app describe commands.
  • Boundary markers: The skill uses markdown tables to present app data to the user, providing visual separation.
  • Capability inventory: The agent has access to Bash for command execution and file system operations.
  • Sanitization: No explicit sanitization of catalog metadata is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:07 AM
Security Audit — agent-trust-hub — cawcut-app-run