impeccable-design-polish
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and modify existing HTML and web artifacts, which represents an attack surface for indirect instructions.
- Ingestion points: The instructions in
SKILL.mdrequire the agent to "Inspect the current HTML/page before editing." - Boundary markers: There are no explicit delimiters or instructions to ignore embedded prompts within the artifact being audited.
- Capability inventory: The skill possesses the capability to modify files ("Polish: directly edit the artifact") and harden layouts.
- Sanitization: No sanitization or validation logic is specified for the content of the HTML artifacts before processing.
Audit Metadata