setup
What this skill does
Installs skills, knowledge, and config for Claude Code or Cursor by executing a setup script
github/tetherto - Command Injection - 321 stars
Threat analysis
Skill info
pkg:github/tetherto/qvac@26898c0?skill=setupAssessments (2)
Command Injection
Command Injection via local-llm-review
SKILL.md
The command `bash packages/ocr-onnx/.agent/setup.sh $ARGUMENTS` uses `$ARGUMENTS` directly without validation or sanitization, which could allow an attacker to inject arbitrary shell commands.Path Traversal
Path Traversal via local-llm-review
SKILL.md
The script path `packages/ocr-onnx/.agent/setup.sh` is hardcoded and not validated, potentially allowing an attacker to manipulate the path to access unintended files or execute malicious scripts.Badge
Add the Anomity scan badge for setup 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 setup? Report an issue or request a rescan.
