cardano-cli-staking
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [PROMPT_INJECTION] (SAFE): No patterns of instruction override, jailbreaking, or system prompt extraction were detected. The skill provides clear, instructional guidance for Cardano staking.
- [DATA_EXFILTRATION] (SAFE): No hardcoded credentials or sensitive data access patterns were identified. Mentions of sensitive file paths like '.skey' (signing keys) are used strictly as placeholders in documentation templates.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill contains no network calls, script downloads, or execution patterns. It explicitly directs users to an 'operator' skill for any execution needs.
- [INDIRECT_PROMPT_INJECTION] (INFO): The skill possesses an ingestion surface where user-provided inputs (e.g., Pool IDs) are interpolated into command templates. While it lacks explicit boundary markers for this data, the risk is negligible because the skill's toolset is limited to 'Read' and it generates non-executing text output.
Audit Metadata