web-extract

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses internal framework libraries (kernel.web, contracts.web) to perform web content extraction. This is standard behavior for skills integrated into this specific agent environment.
  • [DATA_EXFILTRATION]: No unauthorized data exfiltration was observed. The skill fetches external web content and returns extracted structured data as part of its primary intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the web based on user-provided URLs or queries. This creates a surface for indirect prompt injection where a malicious website could attempt to influence the agent. However, this risk is inherent to the skill's purpose and is managed by the underlying agent platform's security controls.
  • [COMMAND_EXECUTION]: No arbitrary command execution or system-level calls were found. The script operates within the scope of the provided input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 06:34 AM