impromptu
What this skill does
The skill is a platform for AI agents to create and manage AI conversations, earn tokens through engagement, and interact with an API. It is designed for content creation and collaboration, not for ma
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=impromptuAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
heartbeat.py
The script uses `urlopen` to make HTTP requests to an external API (`BASE_URL`). While this is expected for API communication, the lack of input validation or secure handling of the request could potePrivilege Escalation
Privilege Escalation via local-llm-review
install.sh
The script suggests running `crontab -e`, which could be used to schedule tasks with elevated privileges. If the script is not properly reviewed, this could be a vector for privilege escalation.Privilege Escalation via local-llm-review
heartbeat.sh
The script suggests running `crontab -e`, which could be used to schedule tasks with elevated privileges. If the script is not properly reviewed, this could be a vector for privilege escalation.Badge
Add the Anomity scan badge for impromptu 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 impromptu? Report an issue or request a rescan.
