task-breakdown
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and templates designed to assist with task management. No executable scripts, binary files, or network-enabled tools are referenced or utilized.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided task descriptions, which constitutes a surface for indirect prompt injection.
- Ingestion points: User tasks and descriptions provided during the breakdown process in
SKILL.md. - Boundary markers: The instructions do not specify clear delimiters or warnings to ignore embedded instructions within user-provided text.
- Capability inventory: The skill's capabilities are limited to generating markdown output and saving it to specific local directories (e.g.,
tasks/). It lacks network access, shell execution, or high-privilege file operations. - Sanitization: There is no explicit sanitization or validation logic defined for the external task data processed by the agent.
Audit Metadata