sillytavern-extension-dev

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements local Node.js scripts (scaffold-extension.mjs, validate-extension-manifest.mjs, check-extension-capabilities.mjs) to automate the development lifecycle of UI extensions. These scripts perform static validation of JSON manifests and use regular expressions to inspect source code for exports without executing the code itself.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data as it reads and processes third-party extension manifests and source files provided by the user.
  • Ingestion points: Files are read in scripts/validate-extension-manifest.mjs and scripts/check-extension-capabilities.mjs using fs.readFileSync based on user-supplied path arguments.
  • Boundary markers: The SKILL.md instructions explicitly separate static validation from runtime acceptance and warn against installation without user authorization.
  • Capability inventory: The scripts possess file system read/write capabilities but no network access. scaffold-extension.mjs can create directories and write files to a designated output root.
  • Sanitization: Both the validator and the scaffolder implement robust path traversal checks using path.resolve and verifying that resolved paths remain within the intended root directory (e.g., resolved.startsWith(root)). This effectively mitigates directory traversal attacks via malicious manifest paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:36 AM
Security Audit — agent-trust-hub — sillytavern-extension-dev