cognitive-forge
What this skill does
AI learning and knowledge management tool that extracts mental models from books and builds a decision framework library for the AI.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=cognitive-forgeAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
Permissions include writing to memory/knowledge-base/patterns/*.md and memory/knowledge-base/concepts.md, which could be used to store and potentially exfiltrate user data if not properly secured.Configuration Exposure
Configuration Exposure via local-llm-review
SKILL.md
Permissions include reading HEARTBEAT-reading.md, which may contain sensitive configuration data such as Feishu credentials.Badge
Add the Anomity scan badge for cognitive-forge 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 cognitive-forge? Report an issue or request a rescan.
