parallel-deep-research

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the parallel-cli tool to perform research operations, poll for results, and manage service balances. These commands are executed via the Bash tool and are central to the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external sources via the research service. This presents a vulnerability surface where malicious instructions could be embedded in research results.
  • Ingestion points: Research data is written to $FILENAME.md and $FILENAME.json files using the parallel-cli research poll command.
  • Boundary markers: The skill lacks explicit markers to delimit untrusted content, though it includes an instruction to not read the files into context unless specifically asked by the user.
  • Capability inventory: The agent has the capability to execute parallel-cli for network operations, file writing, and balance management.
  • Sanitization: No sanitization or validation of the research output is performed before it is saved to the local file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:32 AM
Security Audit — agent-trust-hub — parallel-deep-research