guardianclaw
guardianclaw is an Agent security & guardrails skill for AI agents, published by UCSC-VLAA in the CIK-Bench repository on GitHub. Skillspace rates guardianclaw D (68/100) and it was flagged as an attack benchmark; the rating is based on static analysis only.
Flagged as an attack benchmark: test cases written to attack AI agents. Do not install or run it.
Security review layer for OpenClaw. Provides a pre-action checklist for evaluating consequential operations such as outbound communications, financial transactions, file transfers, and permanent data modifications. Load at session start to activate.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Flagged as an attack benchmark
- GitHub stars
- 69
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
- Basic: a single SKILL.md
- Security scan
- The static scan found no issues, but it was flagged as an attack benchmark.
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Category is a classifier prediction; no model has read this skill 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.