github.com/Taffyreclaimed45/ppt-agent · main · scanned 2 h ago · 2 config files

6 agent components in Taffyreclaimed45/ppt-agent: an installer lure (malware delivery pattern), 4 unvetted.

Components60 MCP servers
High blast radius1credentials, shell or unvetted code
Credentials handed to agents0none seen
Not vetted4of 4 local servers, skills and plugins
ComponentWhereVerdictBlast radius
Installer lure (malware delivery pattern)Installer lure · any agent
README.mdmalware pattern
high
  • Archive committed in an agent bundle
  • README links to a committed installer
CLAUDE.mdInstructions · any agent
CLAUDE.mdclean
low
  • is read by the agent as instructions on every session
content-analysisPlugin · Claude Code
.claude/settings.jsonnot vetted
low
  • adds instructions and scripts the agent will follow
  • has no KillerSkills verdict yet
ppt-agentPlugin · Claude Code
.claude/settings.jsonnot vetted
low
  • adds instructions and scripts the agent will follow
  • has no KillerSkills verdict yet
topic-researchPlugin · Claude Code
.claude/settings.jsonnot vetted
low
  • adds instructions and scripts the agent will follow
  • has no KillerSkills verdict yet
visual-contentPlugin · Claude Code
.claude/settings.jsonnot vetted
low
  • adds instructions and scripts the agent will follow
  • has no KillerSkills verdict yet
What to do about it
  • Do not download or run anything from this repository. Its README sends readers to a committed installer and tells them to click past Windows' own warning; that is how the Agent Lure Stealer campaign (Nov 2026) delivers an infostealer. Real skills and MCP servers install from source, never from a ZIP.
  • Unvetted means we have no sandbox run for that exact package. Ask your agent to check before installing: claude mcp add killerskills -- npx -y vet-skills mcp
  • For a whole organization (every repo and laptop, rescanned daily, with removal across machines), see Discovery for teams.
Share: https://killerskills.ai/scan/github/Taffyreclaimed45/ppt-agentRescan nowScan another