autoresearch
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing external research goals and data to generate executable experiments. Ingestion points: Research metrics and hypothesis parameters provided by the user. Boundary markers: No delimiters or ignore-instructions are specified. Capability inventory: Use of shell tools to write and run autoresearch.sh. Sanitization: No data validation or sanitization process is described.
- [DYNAMIC_EXECUTION]: The skill dynamically creates and runs shell scripts as its primary mechanism for conducting research benchmarks.
Audit Metadata