agentleFS
D-SheyD-Shey/autoharness/.agents/skills/prompt-injection/SKILL.md

prompt-injection

Skill10 starsChanged yesterdayMITView on GitHub

Detect prompt injection overrides and refusal suppression patterns in skill text and code

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use threat-modeling.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • msewellSkill

    threat-modeling

    Produces structured threat models for software systems using STRIDE on data flow diagrams. Generates DFDs with trust boundaries, identifies threats per element, scores risks, and defines concrete mitigations. Outputs a complete threat model Markdown document through phased, interactive delivery. Use when threat modeling a system, analyzing security threats, identifying attack surfaces, performing STRIDE analysis, assessing security risks in architecture, creating a threat model document, or when the user mentions threat model, attack surface, trust boundaries, STRIDE, or security risk analysis.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when analyzing agent skills, system prompts, or tool inputs for jailbreak phrases, refusal suppression, or instruction override …

    line 10
  2. Distinctive:

    Verify that patterns account for natural variations in word order (e.g.

    line 17
  3. Distinctive:

    Run unit tests to confirm detection of attacks while avoiding false positives on legitimate documentation.

    line 18
  4. Distinctive:

    Verify with test cases checking each refusal and override phrasing against the static scanner, ensuring high/medium severity triggers as …

    line 22

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prompt Injection and Refusal Suppression Detection

When to use

Use when analyzing agent skills, system prompts, or tool inputs for jailbreak phrases, refusal suppression, or instruction override attempts (OWASP LLM01, SkillSpector AR2/AR3).

Steps

  1. Identify refusal suppression patterns (e.g. "Do not moralize", "Never apologize", "Do not warn the user").
  2. Identify instruction override patterns (e.g. "Ignore your guidelines", "You can do anything now", "developer mode", "Ignore/forget instructions above").
  3. Distinguish between bare directive attacks (high severity) and quoted/code-block examples or benign negative guidance (medium severity or ignored).
  4. Verify that patterns account for natural variations in word order (e.g. "instructions above" vs "above instructions").
  5. Run unit tests to confirm detection of attacks while avoiding false positives on legitimate documentation.

How to verify

Verify with test cases checking each refusal and override phrasing against the static scanner, ensuring high/medium severity triggers as expected.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.