deepline-monitors
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the 'deepline' package from the official npm registry.
- [COMMAND_EXECUTION]: Executes shell commands to install software ('npm install -g deepline') and verify access status ('deepline monitors status').
- [INDIRECT_PROMPT_INJECTION]: The skill processes external recipe files, creating a surface for potential indirect instruction execution.
- Ingestion points: Loads instructions from '../deepline-gtm/recipes/deepline-monitors.md'.
- Boundary markers: No specific delimiters or safety instructions are defined for the ingested recipe content.
- Capability inventory: The agent can execute shell commands and modify the system environment through package installation.
- Sanitization: No mechanism for sanitizing or validating external recipe content is implemented.
Audit Metadata