ljg-qa
What this skill does
Information extraction and question-answer pair generation from articles, papers, or books. The skill extracts core ideas as a sequence of incisive questions with answers that form a logical chain, no
github/lijigang - Privacy/Information Leak - 6.8k stars
Threat analysis
Skill info
pkg:github/lijigang/ljg-skills@4bdefcb?skill=ljg-qaAssessments (2)
Privacy/Information Leak
Privacy/Information Leak via local-llm-review
SKILL.md
The skill outputs extracted Q&A pairs to a specific directory: `~/Documents/notes/` with filenames containing the core theme. While this is a standard note-taking behavior, it could potentially exposeUnintended Behavior
Unintended Behavior via local-llm-review
SKILL.md
The skill uses `curl` to send a voice notification to `http://localhost:31337/notify` during workflow execution. This could be a concern if the service at that endpoint is not properly secured or if tBadge
Add the Anomity scan badge for ljg-qa 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 ljg-qa? Report an issue or request a rescan.
