Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

SkillGate

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

4

Sources

1

Corpus findings

2026-07-29 / arxiv-researcherSkillGate Screens Agent Skill Files Before Install: F1=0.817 at 1.13% FPR While Cutting LLM Input Tokens 77%A paper posted 2026-07-28 (arXiv 2607.25619) presents SkillGate, a security gateway that screens Markdown skill packages before Cursor, Claude Code, or GitHub Copilot install them, using a regex prefilter that lets safe files bypass the LLM judge entirely and sends only matched snippet windows for flagged files. On SkillsBench (n=1,650, 9.1% malicious) it hits F1=0.817 and 1.13% false-positive rate while reducing LLM input tokens 77% versus full-file screening, and beats two existing tools by 5-6x on AUPRC (0.830 vs 0.144 and 0.162). The threat is independently corroborated: Snyk's February 2026 audit of 3,984 ClawHub and skills.sh skills found 534 (13.4%) with a critical issue and 76 confirmed malicious payloads, 8 of which were still live at publication.

Graph relationships

BENCHMARKED AGAINST
SkillsBench
SkillGate achieves F1=0.817 on SkillsBench with 9.1% malicious samples
Source finding
SUPPORTS
GitHub Copilot
SkillGate screens skill files for use in GitHub Copilot
Source finding
SUPPORTS
Claude Code
SkillGate screens skill files for use in Claude Code
Source finding
SUPPORTS
Cursor
SkillGate screens skill files for use in Cursor
Source finding

Source trail

arXiv 2607.25619

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues