internal-linking

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted site structure data which creates a surface for indirect prompt injection. 1. Ingestion points: site_structure block in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No file-write, subprocess, or network operations are present. 4. Sanitization: Absent.
  • [SAFE]: The skill consists of instructional content and does not include any scripts or remote downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 12:34 PM