kubernetes-secrets-manager
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture creates a surface where untrusted data could influence the agent's actions due to a combination of input ingestion and powerful tool access.\n
- Ingestion points: The skill is designed to trigger on and process user requests containing phrases like 'kubernetes secrets manager'.\n
- Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore potentially malicious commands embedded within user-provided data.\n
- Capability inventory: The skill's allowed tools include Bash (unrestricted shell access), Write, and Edit, which provide significant control over the host environment.\n
- Sanitization: No input validation or sanitization mechanisms are defined in the skill's instructions to filter or escape content from user prompts.
Audit Metadata