ng-verify-feature
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown and a standard Apache 2.0 license file. No malicious code, obfuscation, or persistence mechanisms were detected. The instructions incorporate security best practices, such as warning against the exfiltration of authentication tokens and requiring user authorization for environment modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to interact with and inspect rendered web pages, which serves as a potential vector for indirect prompt injection from untrusted external content.
- Ingestion points: Browser DOM, accessibility observations, and rendered page state as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed web content.
- Capability inventory: Interaction with browser sessions and Chrome DevTools.
- Sanitization: The instructions explicitly require the agent to exclude credentials and sensitive content from evidence and reports.
Audit Metadata