dev-task
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were found. The skill is entirely composed of Markdown-based guidelines and templates for task management.
- [NO_CODE]: The skill does not include any executable scripts or binary files, minimizing the risk of direct malicious code execution.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves reading and processing external task descriptions, creating a potential surface for indirect prompt injection. 1. Ingestion points: Task files located in tasks/items/ and user input. 2. Boundary markers: Uses structured Markdown and JSON templates to separate instructions from data. 3. Capability inventory: The skill guides an agent that can perform file system operations and command execution. 4. Sanitization: No specific input sanitization is defined, though the skill mandates user confirmation for destructive actions.
Audit Metadata