kosis-stats
What this skill does
The skill is a legitimate tool for querying Korean official statistics from the KOSIS Open API. It is designed for data retrieval only and does not perform any modification, analysis, or visualization
github/nomadamas - Privilege Escalation - 7.1k stars
Threat analysis
Skill info
pkg:github/NomaDamas/k-skill@44fbaca?skill=kosis-statsAssessments (2)
Privilege Escalation
Privilege Escalation via local-llm-review
scripts/run_kosis_stats.py
The script uses an API key (`KSKILL_KOSIS_API_KEY`) for authentication, which is a sensitive credential. If this key is not properly protected, it could be misused to access KOSIS data without authoriObfuscation
Obfuscation via local-llm-review
scripts/run_kosis_stats.py
The script contains a URL (`DATA_URL = "https://kosis.kr/openapi/Param/statisticsParameterData.do"`) that may be used to access KOSIS data. While this is legitimate, the URL is obfuscated and not cleaBadge
Add the Anomity scan badge for kosis-stats 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 kosis-stats? Report an issue or request a rescan.
