gate-info-addresstracker

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and presents untrusted data from the blockchain that could be manipulated by third parties.
  • Ingestion points: The skill retrieves address labels, risk scores, and transaction metadata via MCP tools info_onchain_get_address_info, info_onchain_get_address_transactions, and info_onchain_trace_fund_flow as defined in SKILL.md.
  • Boundary markers: The output is structured using Markdown templates, but the skill does not provide specific instructions to the agent to treat external strings as non-executable data or to ignore embedded commands.
  • Capability inventory: The skill's capabilities are restricted to read-only information retrieval and report generation, which significantly limits the potential for harm from an injection.
  • Sanitization: The documentation does not specify any sanitization, filtering, or escaping of external data strings before they are included in the generated reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:01 PM