mfds-drug-safety
What this skill does
Public health safety check using Mfds (Korea Food and Drug Administration) OpenAPI, with an emphasis on drug safety and emergency response based on user symptoms and medication use.
github/nomadamas - Data Exfiltration - 7.1k stars
Threat analysis
Skill info
pkg:github/NomaDamas/k-skill@44fbaca?skill=mfds-drug-safetyAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/mfds_drug_safety.py
The script uses `urllib` to make requests to a proxy server (`k-skill-proxy`) and does not explicitly validate or sanitize the input before sending it. This could allow for unintended data to be sent Configuration Management
Configuration Management via local-llm-review
instruction.md
The `KSKILL_PROXY_BASE_URL` environment variable is used to configure the proxy URL, but there is no explicit guidance on how to securely manage or validate this configuration. If misconfigured, it coBadge
Add the Anomity scan badge for mfds-drug-safety 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 mfds-drug-safety? Report an issue or request a rescan.
