scenario-analyzer

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted data from user-provided headlines and external news content retrieved via the "WebSearch" tool and interpolates it into sub-agent instructions.
  • Ingestion points: User input (headline) in the main workflow and external web content from the "WebSearch" tool used by the "scenario-analyst" agent.
  • Boundary markers: Absent. The skill uses Markdown headers to organize data but does not include explicit instructions to the LLM to ignore or treat embedded directives in the untrusted input as data only.
  • Capability inventory: The agent has the ability to write files to the "reports/" directory and execute network-enabled tools ("WebSearch").
  • Sanitization: No sanitization, validation, or escaping of the external content is implemented before it is processed by the sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:22 PM
Security Audit — agent-trust-hub — scenario-analyzer