ns-sdd-execution-handoff-generator
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design. It processes external data (task files and requirements) to determine the execution logic and instructions for a downstream agent.
- Ingestion points: The agent reads contents from
{product_root}/docs/versions/{version_san}/tasks/task-*.mdandrequirements.mdto populate the handoff file. - Boundary markers: There are no explicit instructions or delimiters in the templates or logic to disregard potentially malicious instructions embedded within the source task files.
- Capability inventory: The skill has the ability to read and write files within the project root and facilitates the dispatch of secondary agents (
coder-agent,reviewer-agent) to perform coding tasks. - Sanitization: The skill does not perform sanitization or validation of the text content extracted from the task files before using it to populate the handoff document.
- [DYNAMIC_EXECUTION]: The skill dynamically generates a "Prompt for implementer" section within the
execution-handoff.mdfile using theexecution-handoff.template.md. This generated content serves as the primary instructions for the implementer agent, allowing the behavior of the next stage in the pipeline to be influenced at runtime based on the contents of the planning phase artifacts.
Audit Metadata