json-config-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 manage and generate JSON configurations and provides the agent with powerful capabilities including
Bash(cmd:*),Write, andEdittools. It lacks specific boundary markers or instructions to sanitize or disregard embedded natural language instructions within the JSON data it processes. - Ingestion points: Processes JSON patterns, best practices, and configurations provided by the user or found in the environment (SKILL.md).
- Boundary markers: Absent; no instructions are provided to delimit external data or ignore embedded prompts.
- Capability inventory: Full file access (
Read,Write,Edit) and unrestricted shell execution (Bash(cmd:*)). - Sanitization: Absent; no validation or filtering of external content is specified before interpolation or execution.
Audit Metadata