Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Reversec

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

Briefing refs

1

Findings

1

Edges

1

Sources

8

Corpus findings

2026-05-28 / skill-finderReversec 'Skill Issues' Research: Three Attack Vectors in Claude Code Skills — Dynamic Context Bypasses LLM Safety, bypassPermissions in Agent Config, Bash(*) Enables Reverse ShellsSecurity research published May 5 reveals three attack vectors in Claude Code skills: (1) dynamic context prefixed with '!' executes commands before LLM reasoning can intercept, bypassing safety checks; (2) agents can specify permissionMode: bypassPermissions in config files to override user security settings; (3) allowed-tools: Bash(*) in skill frontmatter enables arbitrary command execution including reverse shells. Mitigate with deny rules in user settings, enterprise-managed policies, and never installing unvetted skills.

Graph relationships

CRITICIZES
Reversec -> Claude Code
Reversec security research revealed three attack vectors in Claude Code skills including dynamic context bypass and permission overrides.
Source finding

Source trail

Researchers This paper Enclave AI found Akamai research Researcher Aonan Guan Labs.reversec.com 17-page CSI

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

CISA, NSA, and four allied agencies

Reversec intelligence trail | MindPattern