design-handoff
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external design artifacts (such as briefs, personas, and requirements) to generate structured documentation, which presents a surface for indirect prompt injection attacks.
- Ingestion points: In Step 1 of
SKILL.md, the agent is instructed to gather external artifacts like design briefs and personas which are then used to populate the component specifications. - Boundary markers: The skill does not define specific delimiters or instructions to the LLM to ignore potentially malicious instructions embedded within the design artifacts.
- Capability inventory: The skill's capabilities are limited to writing Markdown files to the local path
docs/designpowers/handoff/. It does not possess network or shell execution capabilities. - Sanitization: There is no evidence of sanitization, validation, or escaping of the ingested external content before it is interpolated into the final output documents.
Audit Metadata