asset-templates

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill logic is confined to reading internal assets and formatting text output. No suspicious network activities or system-level risks were detected.
  • [PROMPT_INJECTION]: The skill processes untrusted user data into templates, creating a surface for indirect prompt injection. 1. Ingestion points: User-provided data for placeholders. 2. Boundary markers: Absent. 3. Capability inventory: Uses read_skill_resource to access local assets. 4. Sanitization: No sanitization of user input is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 08:27 AM