elasticsearch-index-manager
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided queries and generate configurations or execute tasks related to DevOps infrastructure. It possesses a high-privilege capability set that creates an attack surface for indirect instructions.
- Ingestion points: Processes natural language user requests containing terms like "elasticsearch", "kubernetes", or "terraform" through the SKILL.MD triggers.
- Boundary markers: No specific delimiters or "ignore embedded instruction" warnings are provided in the instructions to the agent when processing external content.
- Capability inventory: Access to arbitrary shell command execution (
Bash(cmd:*)), file reading/writing/editing (Read,Write,Edit), and searching (Grep). - Sanitization: Lacks sanitization or validation logic to filter potentially malicious instructions within user-provided DevOps patterns or request bodies.
Audit Metadata