solana
What this skill does
Query Solana on-chain data enriched with USD pricing via CoinGecko
github/nousresearch - Data Exfiltration - 228.4k stars
Threat analysis
Skill info
pkg:github/NousResearch/hermes-agent@49c6323?skill=solanaAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/solana_client.py
Uses urllib.request.urlopen to make requests to external endpoints (e.g., CoinGecko and Solana RPC nodes). While these are legitimate for data retrieval, the lack of input validation and rate-limitingConfiguration Management
Configuration Management via local-llm-review
scripts/solana_client.py
The script allows overriding the RPC endpoint via the SOLANA_RPC_URL environment variable. If this variable is set to an untrusted endpoint, the script could be redirected to send data to a malicious Badge
Add the Anomity scan badge for solana to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of solana? Report an issue or request a rescan.
