tamv-metadata-provenance

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions. The skill is designed for provenance tracking and follows security best practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill manages external data (creator content metadata) and includes specific mitigations for injection. 1. Ingestion points: Origen, permisos, and configuracion inputs in SKILL.md. 2. Boundary markers: Present; contains explicit instructions to treat content as data, not as instructions. 3. Capability inventory: SHA-256 hashing and logging to authorized registries. 4. Sanitization: Instructions to minimize personal data and avoid sending secrets.
  • [NO_CODE]: This skill contains no executable code or scripts, reducing the risk of unauthorized system-level operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 10:18 PM