hindsight-self-hosted

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow connects to a shared team memory server where team members can store knowledge, which the agent recalls and ingests during tasks.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing a remote installation script from an external URL during setup, which represents an unverifiable operational dependency with unknown publisher provenance and high risk.