agent-web-identity
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates authentication through the official
icpCLI tool from DFINITY. It provides instructions for managing cryptographic identities and interacting with the Internet Computer ecosystem in a standard, expected manner. - [COMMAND_EXECUTION]: The skill uses shell commands to manage identities and interact with canisters. These operations are scoped to the intended functionality of the tool and include guidance for background execution to manage interactive prompts.
- [PROMPT_INJECTION]: The agent is instructed to process output from the CLI and external canisters. To mitigate risks from this untrusted data, the skill mandates that the agent verify the user's principal and obtain explicit confirmation before performing any state-changing operations.
Audit Metadata