lp-optimizer
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (MEDIUM): The skill is designed to ingest and process untrusted external data from URLs or raw HTML provided by the user. This creates an attack surface where an attacker can hide instructions in the analyzed web page (e.g., in HTML comments or metadata) to influence the agent's behavior.
- Ingestion points: Phase 1, Step 1 ('対象LPのURL or HTMLを取得').
- Boundary markers: Absent; the instructions do not specify any delimiters or ignore-instructions markers to separate external data from processing logic.
- Capability inventory: The skill generates specific implementation code and prioritized recommendations. While it does not execute code directly, it produces outputs that influence user decisions and code deployment.
- Sanitization: Absent; there are no instructions to validate or sanitize external content before analysis.
Audit Metadata