mantella-config
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from multiple sources.
- Ingestion points: The skill targets file types like ENVIRONMENT.md, TASK.md, logs, and binary formats such as ESM, ESP, and DLL as evidence sources.
- Boundary markers: The instructions lack explicit requirements for using delimiters when processing external content, although they do mandate credential redaction.
- Capability inventory: The skill possesses file-writing capabilities to 'edit, merge, or diagnose' configuration and source code.
- Sanitization: No explicit sanitization or filtering of external file content is mandated prior to processing or interpolation into prompts.
Audit Metadata