hindsight-self-hosted

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for an API key and shows a config-file/command snippet that embeds the API key verbatim, which requires the LLM to handle and output secret values directly.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill issues runtime memory recall calls to a self-hosted Hindsight server (api_url e.g. https://hindsight.mycompany.com) whose returned memories are injected into the agent's context and thus directly influence prompts/behavior, making that external endpoint a required runtime dependency.