pine-script-dev
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to interact with the local filesystem using absolute Windows directory paths (D:\down\trading-view) through the Bash and Write tools. The use of hardcoded absolute paths rather than relative paths is a security concern as it targets specific host locations.
- [PROMPT_INJECTION]: The skill uses a workflow based on user-provided 'Requirement Templates' (Pine_任务需求模板.md), creating an indirect prompt injection surface where untrusted user data can influence code generation and file operations. 1. Ingestion points: User-filled sections in the markdown template and subsequent prompts. 2. Boundary markers: None present in the provided templates to isolate user input from instructions. 3. Capability inventory: Access to Write, Edit, and Bash tools as defined in the skill configuration. 4. Sanitization: No evidence of input validation, filtering, or escaping for the user-provided requirement fields.
Audit Metadata