parallel-web-extract

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes parallel-cli through the Bash tool to perform its primary function of URL extraction using user-provided arguments. This is a vendor-owned resource for the 'parallel-web' platform.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external web content.
  • Ingestion points: Untrusted data enters the agent's context through external URLs fetched via parallel-cli in SKILL.md.
  • Boundary markers: The instructions do not specify any markers or delimiters to separate untrusted web content from the agent's own instructions.
  • Capability inventory: The skill environment permits shell command execution (Bash), which could be targeted if the agent follows malicious instructions found within the fetched content.
  • Sanitization: No sanitization, filtering, or instruction-detection logic is applied to the content returned from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 11:48 PM
Security Audit — agent-trust-hub — parallel-web-extract