mechanic-task-writer
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of instructional markdown files and a JSON resource file containing templates. It does not include any executable code for the agent environment or scripts that perform operations outside the scope of documentation and assistance.\n- [PROMPT_INJECTION]: Directives within the instructions define the agent's task-specific persona and do not attempt to bypass safety filters or reveal system prompts. Regarding indirect injection risks, the skill mandates the use of the | json filter for all data interpolation, which provides sanitization for external data processed by generated tasks.\n- [DATA_EXFILTRATION]: No hardcoded credentials or sensitive file paths were identified. Network operations mentioned are standard features of the Mechanic platform.\n- [EXTERNAL_DOWNLOADS]: References to external documentation and repositories target official Lightward and Shopify resources.
Audit Metadata