yield-dashboard
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly read-only and does not include any functions for performing transactions, moving funds, or modifying on-chain state.
- [EXTERNAL_DOWNLOADS]: The skill connects to the Hiro API and the Bitflow public API to retrieve live protocol data and market statistics. These are well-known services in the Stacks ecosystem, and the network activity is consistent with the skill's stated purpose of cross-protocol yield monitoring.
- [PROMPT_INJECTION]: While the skill ingests external data from third-party APIs (representing a surface for indirect prompt injection), it treats this data as structured information for numerical calculation and display. No patterns of direct prompt injection or attempts to override agent behavior were found.
- [DATA_EXFILTRATION]: Analysis of the source code confirms there are no attempts to access sensitive local files (such as SSH keys or environment variables) or to exfiltrate data to unauthorized domains.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, private keys, or other sensitive credentials were found in the skill's scripts or configuration files.
Audit Metadata