gate-info-addresstracker

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes maintenance scripts (update-skill.sh and update-skill.ps1) that download content from the vendor's official GitHub repository (github.com/gate/gate-skills). This is a standard vendor-managed self-update mechanism and is documented neutrally.\n- [COMMAND_EXECUTION]: The update scripts execute system commands including git, tar, and unzip to synchronize and replace skill files within the local directory.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the processing of external blockchain data.\n
  • Ingestion points: Untrusted data enters the agent context via info_onchain_get_address_info, info_onchain_get_address_transactions, and info_onchain_trace_fund_flow.\n
  • Boundary markers: The skill does not employ delimiters or explicit instructions to distinguish external blockchain data from the agent's internal logic within the report templates.\n
  • Capability inventory: The skill can perform shell command execution and modify its own source files through the included maintenance scripts.\n
  • Sanitization: There is no evidence of escaping, validation, or filtering of external blockchain content (such as labels or transaction details) before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 03:51 PM