github.com/intercom/intercom-openapi · main · scanned 2 h ago · 3 config files

3 agent components in intercom/intercom-openapi: 1 unvetted.

Components30 MCP servers
High blast radius0credentials, shell or unvetted code
Credentials handed to agents0none seen
Not vetted1of 1 local servers, skills and plugins
ComponentWhereVerdictBlast radius
CLAUDE.mdInstructions · any agent
CLAUDE.mdclean
low
  • is read by the agent as instructions on every session
generate-openapi-from-prSkill · Claude Code
.claude/skills/generate-openapi-from-pr/SKILL.mdnot vetted
low
  • adds instructions and scripts the agent will follow
  • has no KillerSkills verdict yet
UserPromptSubmitHook · Claude Codeopenapi-skill-auto-inject.sh
.claude/settings.jsonlocal command
low
  • runs `openapi-skill-auto-inject.sh` on every tool call, as the developer
What to do about it
  • 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/intercom/intercom-openapiRescan nowScan another