create-tasks
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for breaking down complex requirements into engineering tasks using Example Mapping, SPIDR, and INVEST criteria. All instructions are oriented toward project management and code architecture without involving suspicious operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which constitutes an attack surface, though impact is mitigated by the lack of high-risk capabilities.
- Ingestion points: Ingests product requirements documents (PRDs), bug reports, and user conversation history to generate tasks as described in the 'Process' section of SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to disregard malicious prompts embedded within ingested requirement data.
- Capability inventory: The skill's output is limited to markdown text generation; no tool access, file system writes, or network operations are specified.
- Sanitization: No validation or sanitization procedures for external requirement content are mentioned.
Audit Metadata