install-gemini-code-review-action

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 their Gemini API key and to insert it verbatim into a shell command (echo "<API_KEY>" | gh secret set ...), 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: 0.90). The skill instructs fetching and using remote workflow and prompt files at runtime (which directly control prompts) from https://raw.githubusercontent.com/derailed-dash/gemini-review-action/main/starter-examples/gemmi-review.yml, https://raw.githubusercontent.com/derailed-dash/gemini-review-action/main/starter-examples/gemini-triage.yml, https://raw.githubusercontent.com/derailed-dash/gemini-review-action/main/starter-examples/gemini-review.toml, https://raw.githubusercontent.com/derailed-dash/gemini-review-action/main/starter-examples/gemini-triage.toml and also relies on the remote action repository https://github.com/derailed-dash/gemini-review-action which is executed by the workflows.