legal-ai-audit-bundle
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The primary script,
scripts/assemble-bundle.mjs, is a zero-dependency Node.js utility that performs file organization, hashing, and manifest generation locally within the agent's environment. - [DATA_EXPOSURE]: The skill instructions provide specific guidance on excluding pseudonymization maps (PII) from audit bundles to comply with RODO (GDPR) requirements, promoting secure handling of sensitive legal data.
- [COMMAND_EXECUTION]: The script uses standard
node:fsmodules to copy files and create directories based on a provided descriptor. These operations are within the scope of the skill'sallowed-tools(Read, Write, Bash). - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through a JSON descriptor. 1. Ingestion points:
descriptor.jsonread inscripts/assemble-bundle.mjs. 2. Boundary markers: None. 3. Capability inventory: The script performsmkdirSync,copyFileSync,writeFileSync, andreadFileSyncinscripts/assemble-bundle.mjs. 4. Sanitization: The script usesbasename()for destination paths to prevent directory traversal outside the bundle target. - [EXTERNAL_DOWNLOADS]: The skill references established patterns from Microsoft and ICME for audit logs as roadmap inspiration but does not download or execute remote code at runtime.
Audit Metadata