tw-research-hypothesis-generator

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It is designed to ingest untrusted data from multiple sources which could theoretically contain instructions to override the agent's behavior.
  • Ingestion points: User-provided research questions or literature review gaps (Step 2) and external content retrieved via the WebSearch tool (Step 3).
  • Boundary markers: The instructions do not define explicit delimiters (e.g., XML tags or Markdown blocks with warnings) to isolate external content from the system instructions.
  • Capability inventory: The skill is granted access to powerful tools including Bash (for command execution) and Write (for file system modification).
  • Sanitization: No explicit sanitization, filtering, or validation of the ingested research data or search results is mentioned before the data is interpolated into the reasoning process.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 12:51 PM