design-review

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: Vulnerability surface identified where the skill ingests untrusted data for analysis. 1. Ingestion points: User-specified target files (SKILL.md). 2. Boundary markers: Absent; there are no instructions to ignore embedded commands. 3. Capability inventory: File reading and text output generation; no network, shell, or file-writing tools are utilized in the instructions. 4. Sanitization: Absent; the skill does not filter or escape the content of the files it reviews.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:06 PM
Security Audit — agent-trust-hub — design-review