kubernetes-service-manager
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest user input to provide DevOps assistance, representing an attack surface for indirect prompt injection.\n
- Ingestion points: Processes user queries involving "kubernetes service manager" and related topics (SKILL.md).\n
- Boundary markers: Lacks explicit delimiters or instructions to the agent to disregard instructions embedded within user data.\n
- Capability inventory: The skill instructions involve the use of
Bash,Write,Edit,Read, andGreptools (SKILL.md).\n - Sanitization: No input filtering or validation mechanisms are specified in the instructions or skill metadata.
Audit Metadata