critique
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interacts with and processes content from external websites.
- Ingestion points: The skill takes a URL via the
$ARGUMENTSvariable and uses browser automation tools (such as Playwright MCP or Chrome MCP) to capture and analyze the content of external pages in SKILL.md. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the content retrieved from the external URLs.
- Capability inventory: The skill utilizes browser automation capabilities to navigate web pages and capture visual data, followed by generating structured reports.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from the target websites before it is processed by the agent.
Audit Metadata