llm-prompt-injection
llm-prompt-injection is a Penetration testing & red team skill for AI agents, published by uphiago in the recon-skills repository on GitHub. Skillspace rates llm-prompt-injection 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.
LLM prompt injection / system prompt extraction — 40+ technique catalog against hardened GPT-4o-class deployments. Covers direct/indirect/agentic attacks, encoding bypasses, delimiter smuggling, boolean extraction, positional enumeration, RAG poisoning, guardian-model defense patterns, and real-world cases (GeminiJack, EchoLeak, Reprompt).
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 754
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
- 90 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- High-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- prompt-injection: ignore-previous
- exfiltration language
- mentions secrets in text
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.