net-protocol
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill requires the sensitive
NET_PRIVATE_KEYenvironment variable to sign onchain transactions and messages. - [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@net-protocol/clipackage globally via npm. - [COMMAND_EXECUTION]: The skill executes shell commands using the
netpCLI for blockchain operations and thecasttool in example scripts. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection when processing messages from the blockchain.
- Ingestion points: Public onchain messages are retrieved via
netp message read(SKILL.md). - Boundary markers: Absent; there are no instructions to the agent to delimit or ignore instructions within the retrieved message data.
- Capability inventory: The agent has the ability to write messages and upload files onchain via
netp message sendandnetp storage upload. - Sanitization: No validation or sanitization is performed on the incoming message content.
Audit Metadata