oray
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions provide commands to add an MCP server and install a skill using resources hosted on the vendor's domain, unbrowse.ai.
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it fetches and processes data from the external website oray.com.
- Ingestion points: The
oray_com__read_pagetool inSKILL.mdretrieves content from the oray.com domain for processing. - Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between tool instructions and untrusted data from the external site.
- Capability inventory: The skill possesses read-only capabilities including catalog browsing and reading page text/links as defined in
SKILL.md. - Sanitization: No content filtering or sanitization procedures are described for the data fetched from the external source.
Audit Metadata