hex-install-auth
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting user-supplied configuration data (API tokens) to set up a local environment. This presents a potential surface for indirect injection via the input data. * Ingestion points: User-supplied API credentials referenced in the environment configuration section of SKILL.md. * Boundary markers: None explicitly defined to delimit untrusted input strings. * Capability inventory:
Write(file system access for environment configuration),fetch(network access to the Hex API), andcurl(network access via shell). * Sanitization: The skill includes explicit instructions for the agent to return a 'setup receipt' rather than printing sensitive credentials, which serves as an output-side security measure to prevent accidental data exposure. - [SAFE]: The skill promotes responsible secret management by directing users to store credentials in
.envfiles and ensuring they are excluded from version control using.gitignore.
Audit Metadata