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), and curl (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 .env files and ensuring they are excluded from version control using .gitignore.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — hex-install-auth