mode-creator
What this skill does
The skill is a tool for creating and configuring custom modes for claude-mem, including optional Telegram alerts. It is not inherently a security or teaching tool, but it includes functionality for in
github/thedotmack - Data Exfiltration - 90.3k stars
Threat analysis
Skill info
pkg:github/thedotmack/claude-mem@d768ba3?skill=mode-creatorAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/configure-telegram.mjs
The script uses `process.env` to access environment variables and makes a fetch call to `api.telegram.org/bot`, which could be used to exfiltrate data if the environment variables are misconfigured orPrivilege Escalation
Privilege Escalation via local-llm-review
scripts/configure-telegram.mjs
The script reads `.env` files, which may contain sensitive information such as API keys or credentials. If these files are not properly secured, this could lead to privilege escalation or data exposurBadge
Add the Anomity scan badge for mode-creator 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 mode-creator? Report an issue or request a rescan.
