jules-and-lobster
What this skill does
The skill is a wrapper for interacting with the Jules REST API (v1alpha) to manage sources, sessions, activities, and outputs. It is intended for delegating coding tasks to Jules programmatically and
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=jules-and-lobsterAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/jules_api.sh
The script uses the JULES_API_KEY environment variable, which is a sensitive credential. If this key is compromised, it could be used to access the Jules API and potentially exfiltrate data.Insecure Dependency
Insecure Dependency via local-llm-review
SKILL.md
The skill requires the 'curl' and 'python3' dependencies, which are not inherently insecure. However, if these dependencies are not properly managed or updated, they could introduce vulnerabilities.Badge
Add the Anomity scan badge for jules-and-lobster to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of jules-and-lobster? Report an issue or request a rescan.
