content-wireframe
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions involve reading external data such as competitor websites and local project files (e.g., AGENTS.md, README.md, data modules). While this creates an entry point for untrusted data (Indirect Prompt Injection surface), the skill is purely instructional for text generation and lacks any dangerous capabilities like code execution, file system modification, or network exfiltration that could be exploited by such an injection. All outputs are intended for human review.
- [DATA_EXFILTRATION]: The skill recommends accessing project-specific context and crawling competitor pages to inform the wireframe content. There are no patterns indicating that this information is sent to any external or unauthorized destinations. The processing is confined to generating a local markdown blueprint for the user.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, external script downloads, or package installations were detected. The skill consists only of instructional text and does not include executable scripts.
- [COMMAND_EXECUTION]: There are no instances of shell command execution, privilege escalation attempts, or persistence mechanisms within the skill instructions.
Audit Metadata