Jules API

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: jules-api Version: 1.0.0 The OpenClaw AgentSkills skill bundle for the Google Jules API is benign. It provides a legitimate interface to the Jules REST API, allowing users to manage coding sessions. All network requests are directed to the official `jules.googleapis.com` endpoint, and the `JULES_API_KEY` is handled appropriately as an authentication header. The `SKILL.md` documentation and the `scripts/jules.sh` helper script contain no evidence of data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection attempts against the OpenClaw agent. User inputs for JSON payloads are properly escaped using `jq -Rs .` in `jules.sh`, mitigating potential injection risks.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A mistaken or overbroad task could cause Jules to make repository changes or create pull requests before the user has reviewed a plan.

Why it was flagged

The script defaults new coding sessions to no plan approval and supports automatic PR creation, giving the agent a high-impact action path on connected GitHub repositories unless the user deliberately opts into approval.

Skill content
echo "  --approve: require plan approval (default: auto-approve)" ... REQUIRE_APPROVAL="false" ... --auto-pr) AUTOMATION_MODE="AUTO_CREATE_PR"
Recommendation

Default to requiring plan approval, use --auto-pr only after explicit user confirmation, and restrict invocations to a specific repository, branch, and task description chosen by the user.

What this means

Anyone or any agent with access to this API key could interact with the user’s Jules sessions and connected repositories within the key’s permissions.

Why it was flagged

The skill clearly uses a Jules API key and that key enables actions tied to the user’s Jules account and connected GitHub repositories. This is expected for the stated purpose, but it is sensitive account authority.

Skill content
**Auth:** Pass your API key via the `x-goog-api-key` header. ... Jules can autonomously execute coding tasks on your GitHub repositories
Recommendation

Use a dedicated Jules API key if possible, keep it out of logs and shared prompts, and revoke or rotate it if the skill is no longer needed.

What this means

A Jules session may keep working remotely until completion, failure, deletion, or user intervention.

Why it was flagged

The skill intentionally launches work performed by an external autonomous coding agent. This is disclosed and purpose-aligned, but remote sessions may continue after the local command returns.

Skill content
Jules can autonomously execute coding tasks on your GitHub repositories — writing code, fixing bugs, adding tests, and creating pull requests.
Recommendation

Monitor sessions after creation, require plan approval for non-trivial tasks, and delete or pause sessions that are no longer wanted.