ctx-doctor
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a bundled JavaScript CLI tool using Node.js to perform system and runtime diagnostics. The execution path is determined dynamically based on the skill's location within the plugin structure.
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection. 1. Ingestion points: The output of the diagnostic command is processed by the agent to display results in the chat. 2. Boundary markers: No explicit delimiters are provided to the agent to encapsulate the tool output. 3. Capability inventory: The skill has the capability to execute local commands. 4. Sanitization: No sanitization or validation is applied to the diagnostic tool output before re-display.
Audit Metadata