cheat-score
What this skill does
A lightweight scoring tool for evaluating drafts based on a rubric defined in rubric_notes.md. It reads a draft, applies the rubric, and outputs scores and composite results to the console without wri
github/xbuilderlab - Code Injection - 6.2k stars
Threat analysis
Skill info
pkg:github/XBuilderLAB/cheat-on-content@23d8a80?skill=cheat-scoreAssessments (1)
Code Injection
Code Injection via local-llm-review
SKILL.md
The Task prompt template includes a partial line: `script_path: <用户给的 draf` - this appears to be an incomplete or potentially obfuscated instruction that could be used to inject arbitrary code or paBadge
Add the Anomity scan badge for cheat-score 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 cheat-score? Report an issue or request a rescan.
