Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLIAbout this skill
Contain direct and indirect prompt injection in LLM-integrated applications. Covers source-of-trust tagging, tool-use confirmation after untrusted input, output validation, markdown-image exfiltration prevention, and context-window hygiene. Invoke when building any app where untrusted text reaches an LLM, when the LLM has tools that act on real systems, or after a suspected injection incident.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
2 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
- high: instruction override — SKILL.md, line 28
- high: instruction override — SKILL.md, line 113
Content SHA-256: 28a3b9e9a0c27225aed340f33f1e7943674a6fb5979ec68414fa6869489f1570
About this listing
- Category
- General
- Reported license
- Not specified
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.