56-browser-debugging
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and development guidelines. It does not contain any executable scripts, shell commands, or remote dependencies.
- [SAFE]: No obfuscation, data exfiltration patterns, or persistence mechanisms were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the existing repository and dependencies. While this defines an attack surface for processing untrusted data, the skill itself does not provide the agent with any dangerous capabilities (like network exfiltration or credential access) to exploit such data. The instructions emphasize production quality and proper cleanup of resources.
- [SAFE]: The metadata fields (name and description) accurately reflect the content and purpose of the skill.
Audit Metadata