hindsight-cloud

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 then write it directly into a local configuration file via generated shell commands.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and execute an installation script from https://hindsight.vectorize.io/get-cli, establishing a weak operational dependency on an unverified third-party hosting endpoint.