ucp-schema-authoring
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and reference schemas from the official domain
ucp.devand references a validation tool on GitHub (github.com/Universal-Commerce-Protocol/ucp-schema). These operations are consistent with the skill's primary purpose of authoring protocol-compliant schemas. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it retrieves external documentation that is then processed by the agent.
- Ingestion points: External data is ingested via
WebFetchcalls toucp.devas defined inSKILL.md. - Boundary markers: Absent. The instructions do not specify delimiters or constraints for the fetched specification content.
- Capability inventory: The skill has access to
Write,Edit, andBashtools, which could be misused if the external source provided malicious instructions. - Sanitization: Absent. There is no explicit validation of the fetched content beyond its use as a technical reference.
Audit Metadata