z-design-handoff
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes markdown design briefs which serves as an ingestion point for untrusted data.\n
- Ingestion points: Reads content from
docs/design/<slug>-brief.mdto derive tokens, components, and voice.\n - Boundary markers: Absent; there are no delimiters or instructions to ignore potential commands embedded within the brief file.\n
- Capability inventory: The skill performs file system read and write operations, specifically creating
docs/design/<slug>-handoff.md.\n - Sanitization: Absent; the skill does not perform validation or sanitization of the content extracted from the brief.\n- [COMMAND_EXECUTION]: The skill utilizes a shell utility within its verification step.\n
- Evidence: The skill instructs the agent to run
fd -e md . docs/design/to verify that the handoff document was successfully created.
Audit Metadata