skills/helius-labs/core-ai/svm/Gen Agent Trust Hub

svm

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses MCP tools to retrieve content from the Helius blog, Solana documentation, and GitHub source code repositories. These are trusted sources relevant to the skill's educational purpose.
  • [COMMAND_EXECUTION]: The provided install.sh script performs standard file management operations to install the skill locally. These actions are limited to copying files to the user's Claude skills directory.
  • [PROMPT_INJECTION]: The skill is designed to ingest and synthesize data from external sources. While this facilitates access to up-to-date information, it introduces a surface for indirect prompt injection. 1. Ingestion points: SKILL.md (utilizing tools such as fetchHeliusBlog and readSolanaSourceFile). 2. Boundary markers: Not present in the current prompt configuration. 3. Capability inventory: Restricted to information retrieval and synthesis; the skill is explicitly instructed not to perform file writes. 4. Sanitization: No explicit validation or filtering of external content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 10:12 PM