parallel
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'orth' CLI tool to execute API requests to Parallel's web research endpoints.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing content from untrusted external web sources.
- Ingestion points: External data enters via the '/v1beta/search' and '/v1beta/extract' endpoints.
- Boundary markers: No specific boundary markers or 'ignore' instructions are present to isolate fetched content.
- Capability inventory: The skill utilizes API execution via 'orth' for research and summarization tasks.
- Sanitization: Content sanitization is not explicitly handled within the skill's logic.
Audit Metadata