get-block-number

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts a user-provided "Chain name" which is interpolated into Python script logic and environment variable keys (e.g., JSON_RPC_{CHAIN}). This creates a surface where a maliciously crafted chain name could attempt to influence the agent's code generation.
  • Ingestion points: User-supplied chain name variable in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: The skill executes Python scripts via the uv tool.
  • Sanitization: The instructions suggest converting the input to uppercase but do not include explicit validation or escaping logic.
  • [EXTERNAL_DOWNLOADS]: The skill's execution instructions involve uv run, which may download the eth-defi package from the Python Package Index (PyPI). The eth-defi library is an official package maintained by the skill's author, tradingstrategy-ai, and is appropriate for the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 03:18 PM