application-security
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides guidance for processing potentially untrusted data from renderers, webviews, and external files, which represents an indirect prompt injection attack surface. \n
- Ingestion points: Untrusted surfaces are defined in references/current-guidance.md as renderers, webviews, plugins, and external files. \n
- Boundary markers: The skill explicitly instructs to treat every bridge from an untrusted surface as a trust boundary. \n
- Capability inventory: The skill scope includes shell access, filesystem operations, and privileged OS APIs. \n
- Sanitization: Guidelines require keeping sensitive APIs behind narrow adapters and preventing untrusted surfaces from choosing trusted origins.
Audit Metadata