sillytavern-media-live2d-runtime
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON configuration files (manifests and bindings) which represents a vulnerability surface for indirect prompt injection.
- Ingestion points: The scripts
validate-media-manifest.mjs,check-media-bindings.mjs, andplan-media-preload.mjsingest data from local JSON files. - Boundary markers: Not explicitly defined within the processed files, though the scripts use standard JSON parsing which naturally delimits data.
- Capability inventory: The validation scripts are restricted to filesystem read access and cryptographic hashing; they do not perform file writes, network requests, or shell command execution based on the input data.
- Sanitization: The skill implements rigorous schema validation, utilizing regular expressions for identifiers and hashes, and whitelist-based checks for asset types, event names, and lifecycle actions.
Audit Metadata