parallel-web-extract

Pass

Audited by Gen Agent Trust Hub on May 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands through the parallel-cli tool to perform its primary function of data extraction. This use of a CLI tool is consistent with the skill's stated purpose and author context.
  • [EXTERNAL_DOWNLOADS]: The skill connects to and retrieves content from arbitrary external URLs provided by the user. This is the intended behavior for a web extraction tool.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes and displays content from untrusted external sources.
  • Ingestion points: Web content retrieved from external URLs via parallel-cli extract (SKILL.md).
  • Boundary markers: Absent; the instructions require the agent to return the extracted content verbatim without using specific delimiters or safety warnings to isolate the untrusted content.
  • Capability inventory: The skill is restricted to the parallel-cli tool via its allowed-tools configuration.
  • Sanitization: No sanitization or filtering is performed on the extracted content, as the skill's objective is verbatim retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
May 23, 2026, 12:35 AM
Security Audit — agent-trust-hub — parallel-web-extract