FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Prompt injection detection v1.0.0
Use this resource to spot prompt injection in text, a skill or external data
New
- 522 downloads
- 212 likes
- 219 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install prompt-injection-detectionWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent normalises the text, then checks it against known injection patterns: direct, contextual, indirect or social engineering. It gives a reasoned verdict for each suspicious passage.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: threat model and injection categories
- SKILL.md: four-step scan protocol and verdict
Good fit for
- You feed an agent web pages or third-party files
- A skill seems more directive than what it claims to do
Not for
Tags
- prompt injection
- security
- agents
- detection
About
You say
“Scan this text copied from a website: is there an attempt to override the agent's instructions?”
Skill published by useai-pro under the MIT license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to spot prompt injection in text, a skill or external data
- Review and adjust the result
Content preview
Files
- LICENSE1.1 KB
- NOTICE-PALATEKIT.md0.5 KB
- SKILL.md5.7 KB
Origin and licence
Listed unmodified
- Author
- useai-pro
- Source
- github.com/useai-pro/openclaw-skills-security/tree/4645f2d047d63e0682b01745d9fc07720110d386/skills/prompt-guard
- Licence
- MIT
Notice
« prompt-guard » (useai-pro, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…