identify-page-structure
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional content in markdown format and does not contain any scripts, code, or binary files.
- [SAFE]: No hardcoded credentials or sensitive environmental variables were identified within the skill metadata or body.
- [SAFE]: The skill processes local files such as screenshot.png and cleaned.html but does not include any network communication capabilities to exfiltrate this data.
- [SAFE]: The skill analyzes untrusted HTML content, presenting an indirect prompt injection surface. However, it lacks any capability for code execution, file system writing, or network access.
- Ingestion points: The cleaned.html file provided by the scrape-webpage skill.
- Boundary markers: Absent; instructions do not define delimiters for external data.
- Capability inventory: None; the skill has no access to subprocesses, network tools, or shell execution.
- Sanitization: Absent; the skill does not specify filtering or escaping of input content.
Audit Metadata