skills/tonone-ai/tonone/cite-compare/Gen Agent Trust Hub

cite-compare

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection due to its research-focused functionality.
  • Ingestion points: External data is introduced into the agent context via WebSearch and WebFetch tools during the jurisdictional research phase (Step 1).
  • Boundary markers: The instructions lack specific delimiters or warnings to the model to ignore embedded instructions within the fetched regulatory guidance.
  • Capability inventory: The skill's execution environment includes the Bash and Write tools, which could potentially be targeted if an injection occurs.
  • Sanitization: No explicit sanitization or content validation steps are defined for the data retrieved from the web before it is processed for the final artifact.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:50 AM
Security Audit — agent-trust-hub — cite-compare