kubesearch
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing content from external repositories.
- Ingestion points: Uses WebFetch to pull data from kubesearch.dev and raw.githubusercontent.com.
- Boundary markers: No delimiters or protective instructions are used to separate fetched content from agent instructions.
- Capability inventory: Restricted to network reads; no support for command execution, file writing, or credential access.
- Sanitization: Content is ingested directly as fetched without sanitization or validation steps.
Audit Metadata