skills/flux-point-studios/cardano-agent-skills/cardano-cli-transactions-operator/Gen Agent Trust Hub
cardano-cli-transactions-operator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes 'cardano-cli' and standard filesystem utilities ('mkdir', 'cat') exclusively for its intended purpose of managing blockchain transactions. All commands are structured and require user input for variable parameters.
- [DATA_EXFILTRATION] (SAFE): While the skill manages sensitive cryptographic signing keys ('.skey' files), it does so as local file references. There are no hardcoded secrets or network operations that would risk exfiltrating these keys.
- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill ingests external data from the Cardano blockchain (UTXOs and protocol parameters). While this creates an ingestion surface for untrusted data, the risk is mitigated by the skill's operational design which requires human review of transaction details and explicit confirmation before any state-changing action. Ingestion points: utxos.json, pparams.json. Boundary markers: Absent. Capability inventory: cardano-cli (query, build, sign, submit), mkdir, cat, Read, Write. Sanitization: Relies on cardano-cli tool logic for parsing blockchain data.
Audit Metadata