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-clitool to perform research operations, poll for results, and manage service balances. These commands are executed via theBashtool 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
$FILENAME.mdand$FILENAME.jsonfiles using theparallel-cli research pollcommand. - 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-clifor 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