ux-spec
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or unauthorized data access patterns were detected. The skill's operations are strictly confined to reading local project files and writing Markdown documentation.\n- [SAFE]: The skill does not perform any network operations, external downloads, or remote code execution. All external references in the documentation are for attribution or informational purposes and point to well-known repositories or vendor domains.\n- [PROMPT_INJECTION]: The skill ingests data from local files such as
docs/PRD.mdanddocs/ARCHITECTURE.md, creating a theoretical surface for indirect prompt injection. However, the risk is negligible because the skill lacks high-risk capabilities like network access or shell execution.\n - Ingestion points:
docs/PRD.md,docs/ARCHITECTURE.md, andproduct-plan-*.md(referenced inSKILL.md).\n - Boundary markers: Absent; there are no specific markers instructing the agent to ignore instructions within the ingested data.\n
- Capability inventory: The agent is limited to reading specified local text files and writing results to new Markdown files in the
docs/directory.\n - Sanitization: Absent; the skill transforms raw text content from project documents into design specifications.
Audit Metadata