visual-hierarchy
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain scripts, binaries, or network-enabled tools.
- [NO_CODE]: No source code or package manifests were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted layout descriptions or files, representing a theoretical ingestion surface. 1. Ingestion points: Input gathering step in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None; the skill has no access to shell commands or network APIs. 4. Sanitization: Absent. The risk is mitigated by the lack of exploitable capabilities.
Audit Metadata