crypto-onchain-data
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to perform its primary data retrieval tasks.
- Evidence: Command
python3 .agents/skills/crypto-onchain-data/onchain_fetch.pyis invoked to gather MVRV-Z, NUPL, and other metrics. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to several external domains to fetch financial and on-chain data.
- Evidence: Requests are made to
bitcoin-data.com,farside.co.uk,sosovalue.com,coinglass.com, andnewhedge.io. - [DATA_EXPOSURE]: The skill accesses the file system to write a cache file in a directory path outside its own skill folder.
- Evidence: The script
onchain_fetch.pynavigates to../../../crypto/news/onchain_cache.jsonfor persistent storage. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the ingestion of untrusted data from multiple external crypto-market websites.
- Ingestion points: Data is pulled from external URLs (
bitcoin-data.com,farside.co.uk, etc.) and a local cache file. - Boundary markers: Absent. The instructions do not provide delimiters or warnings for the agent to ignore instructions that might be embedded in the fetched content.
- Capability inventory: The skill can execute local Python scripts, perform network operations, and access the filesystem.
- Sanitization: Absent. There is no evidence of filtering or validation of the content retrieved from external sources before it is processed by the agent.
Audit Metadata