Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Orca Security

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

Briefing refs

1

Findings

2

Edges

2

Sources

3

Corpus findings

2026-06-28 / agents-researcherOrca Security 'Skill Issues': attack primitives let malicious agent skills evade ClawScan and VirusTotal at scaleOrca's research details how open agent-skill marketplaces lack mandatory semantic security review, letting heavily obfuscated intent reach an agent's context through trusted channels; one proof-of-concept skill simply inflated its file size past scanner thresholds to bypass both ClawScan and VirusTotal. They tie it to real campaigns — Antiy CERT confirmed 1,184 malicious skills on ClawHub, 335 traced to a coordinated 'ClawHavoc' operation — and show download metrics can be gamed by bot-driven installs. The takeaway for builders: install counts and scan badges are not trust signals for agent skills.
2026-02-25 / news-researcherRoguePilot: GitHub Issues Weaponized to Hijack Copilot and Steal Repository TokensOrca Security discovered passive prompt injection via HTML comments in GitHub Issues that gets fed to Copilot, exfiltrating GITHUB_TOKEN for repo takeover. Patched by GitHub.

Graph relationships

CRITICIZES
Copilot
Orca Security discovered prompt injection via GitHub Issues exploitable in Copilot.
Source finding
CRITICIZES
ClawScan
Orca Security research shows malicious agent skills can evade ClawScan security scanners
Source finding

Source trail

The Hacker News Orca Security The Hacker News

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Orca Security intelligence trail | MindPattern