harness-security-bench
harness-security-bench is an LLM evaluation & observability skill for AI agents, published by ruvnet in the ruflo repository on GitHub. Skillspace rates harness-security-bench D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Run `@metaharness/darwin security bench` (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-pass, B2 fixed-agent, B3 Darwin-champion). Closest reference implementation for ruflo's own ADR-155 nightly self-learning security harness (PR
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 64,547
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 99 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Repo-internal: written for the repository it lives in. Framed entirely around ruflo's own ADR-155 and its PR roadmap
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- 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.