touch-targets
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external HTML and CSS markup, which constitutes a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to find and review interactive elements and rendered markup in SKILL.md.
- Boundary markers: There are no instructions to use delimiters or ignore embedded instructions within the audited content.
- Capability inventory: The skill does not use any tools or commands with side effects (no network, file-write, or shell access), which prevents the exploitation of any potential injection.
- Sanitization: No validation or sanitization of external markup is performed.
Audit Metadata