parallel-deep-research
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
parallel-cliand interpolates the user-provided$ARGUMENTSdirectly into the command string. While the execution is restricted to theparallel-clitoolset via the allowed-tools configuration, unvalidated user input in shell commands remains a potential injection surface. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and displays research summaries derived from external, untrusted sources.
- Ingestion points: The executive summary and report files generated by
parallel-cli research pollas described in Step 2. - Boundary markers: No explicit delimiters or warnings are used to separate research data from the agent's instructions.
- Capability inventory: The skill has access to shell execution via
parallel-cliand file system writes for saving research reports. - Sanitization: There is no evidence of sanitization or filtering applied to the external data before it is presented to the user or stored in the context.
Audit Metadata