prompt-guard
prompt-guard is an Agent security & guardrails skill for AI agents, published by EverClaw in the EverClaw repository on GitHub. Skillspace rates prompt-guard F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Advanced prompt injection defense system for EverClaw with HiveFence network integration. Detects and blocks injection attacks across multiple languages (EN/KO/JA/ZH) with severity scoring, automatic logging, and configurable security policies. Includes external content detection for GitHub issues, PRs, emails, Slack, Discord, and social media. Use when processing untrusted messages, evaluating external content for threats, configuring injection detection, or integrating with the HiveFence threat intelligence network.
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 23
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
- 89 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Critical-risk patterns
- License
- MIT
- Adoption
- Adopted by 4 other repositories, in 0 collections
What the scanner flagged
- pipe remote script to shell
- prompt-injection: ignore-previous
- exfiltration language
- accesses sensitive system files
- 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.