prompt-injection-defense
prompt-injection-defense is an Agent security & guardrails skill for AI agents, published by 0xDarkMatter in the claude-mods repository on GitHub. Skillspace rates prompt-injection-defense F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Defend the agent against adversarial Unicode it obeys but a human can't see: bidi/Trojan Source, tag-char smuggling, zero-width text, homoglyphs. Triggers on: prompt injection, scan for hidden unicode, hidden characters, zero-width space, Trojan Source, ASCII smuggling, poisoned CLAUDE.md, MCP tool poisoning, is this file safe.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 25
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 100 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- exfiltration language
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.