task-breakdown
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external software design documents to generate task breakdowns, which introduces a surface for indirect prompt injection.
- Ingestion points: The workflow begins by reading software design documentation from the environment or user input in the first step of the '步骤' section.
- Boundary markers: The instructions do not define clear delimiters or specific guidance for the agent to treat the contents of the design documents as potentially untrusted data or to ignore embedded instructions.
- Capability inventory: The skill is restricted to text analysis and outputting a list and table; it does not request or demonstrate use of high-risk tools such as shell execution, network access, or file modification.
- Sanitization: No sanitization or validation of the input document content is described in the skill instructions.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no accompanying scripts, executables, or automated logic that could be exploited for direct code execution.
Audit Metadata