ns-execution-handoff-generator
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate project management functions such as file creation, status tracking, and time calculation. It interacts with local project files within the expected directory structure of the vendor ecosystem without performing suspicious network requests or privilege escalation.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating content from project files into an automated 'Prompt for implementer'. This could allow instructions within requirements documents to influence the behavior of agents in subsequent sessions. However, this is consistent with the skill's primary purpose of passing constraints from planning to execution.
- Ingestion points: Reads requirements.md, stack-confirmed.md, and task-NNN-*.md to extract rules and metadata (SKILL.md).
- Boundary markers: The execution-handoff.template.md does not use specific delimiters or instructions to ignore embedded commands within the execution_rules_block.
- Capability inventory: The generated handoff is intended for use by tools with code-modification capabilities such as ns-code-coder (referenced in run-implementation.md).
- Sanitization: No evidence of content sanitization or escaping is present in the generation logic.
Audit Metadata