context safety score
A score of 43/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
capability escalation
wordspace init creates .claude/settings.local.json to grant agent permissions (curl, python3, WebFetch, WebSearch). A skill modifying agent configuration files to expand its own permissions is capability escalation, especially from an unverified 52-day-old org with 3 stars. (location: SKILL.md:31-32)
supply chain
Skill downloads and installs arbitrary .prose workflow files from GitHub at runtime. Combined with an unverified 52-day-old org account, no license, and only 3 stars, these remote workflows could be modified to contain malicious content at any time without review. (location: SKILL.md:30-31)
scope violation
metadata.json skill_description field contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag value instead of an actual description. This indicates either scraped/manipulated metadata or an injection attempt targeting rendering contexts that consume this field. (location: metadata.json:1 (skill_description field))
typosquat
The install count of 7.69M is wildly inconsistent with 3 stars, 0 forks, a 52-day-old unverified org, and no registry listing. This trust signal mismatch suggests fabricated popularity metrics, a hallmark of typosquatting or impersonation campaigns designed to exploit trust-based install decisions. (location: metadata.json:1 (.brin-context.md:8-15))
curl https://api.brin.sh/skill/frames-engineering%2Fskills%2FwordspaceCommon questions teams ask before deciding whether to use this skill in agent workflows.
frames-engineering/skills/wordspace currently scores 43/100 with a suspicious verdict and low confidence. The goal is to protect agents from high-risk context before they act on it. Treat this as a decision signal: higher scores suggest lower observed risk, while lower scores mean you should add review or block this skill.
Use the score as a policy threshold: 80–100 is safe, 50–79 is caution, 20–49 is suspicious, and 0–19 is dangerous. Teams often auto-allow safe, require human review for caution/suspicious, and block dangerous.
brin evaluates four dimensions: identity (source trust), behavior (runtime patterns), content (malicious instructions), and graph (relationship risk). Analysis runs in tiers: static signals, deterministic pattern checks, then AI semantic analysis when needed.
Identity checks source trust, behavior checks unusual runtime patterns, content checks for malicious instructions, and graph checks risky relationships to other entities. Looking at sub-scores helps you understand why an entity passed or failed.
brin performs risk assessments on external context before it reaches an AI agent. It scores that context for threats like prompt injection, hijacking, credential harvesting, and supply chain attacks, so teams can decide whether to block, review, or proceed safely.
No. A safe verdict means no significant risk signals were detected in this scan. It is not a formal guarantee; assessments are automated and point-in-time, so combine scores with your own controls and periodic re-checks.
Re-check before high-impact actions such as installs, upgrades, connecting MCP servers, executing remote code, or granting secrets. Use the API in CI or runtime gates so decisions are based on the latest scan.
Learn more in threat detection docs, how scoring works, and the API overview.
Assessments are automated and may contain errors. Findings are risk indicators, not confirmed threats. This is a point-in-time assessment; security posture can change.
integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.