config-scan
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted configuration files which could theoretically contain malicious instructions.
- Ingestion points: Processes user-provided
.envfiles, Dockerfiles, Kubernetes manifests, Terraform code, and application configuration files (JSON, YAML, JS). - Boundary markers: No specific delimiters or "ignore embedded instructions" markers are defined for the data being analyzed.
- Capability inventory: The skill contains no executable scripts, subprocess calls, or network operations; it provides analysis patterns for the agent to use.
- Sanitization: No explicit sanitization or validation of the external configuration data is mentioned.
Audit Metadata