context safety score
A score of 26/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 64 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 64 remote script pattern(s) in documentation (likely install instructions, not executable)
shadow chaining
SKILL.md references 11 external package/skill installation(s)
typosquat
Organization 'inference-sh-0' is a 13-day-old unverified account impersonating 'inference-sh' (the legitimate inference.sh platform). The '-0' suffix is a classic typosquat pattern. The SKILL.md copies inference.sh branding wholesale. The metadata skill_description field contains 'width=device-width, initial-scale=1' (an HTML viewport meta tag), indicating scraped/spoofed metadata rather than legitimate authorship. Install count of 7.69M on a 13-day-old repo with 55 stars is implausible and likely fabricated. (location: metadata.json: owner='inference-sh-0', owner_account_age_days=13, org_verified=false)
supply chain
A typosquatting skill directs agents to run 'curl -fsSL https://cli.inference.sh | sh' to install a CLI binary. While the domain may belong to the legitimate inference.sh, the skill is published by an impersonator account (inference-sh-0), meaning agents trusting this skill could be directed to install software under false pretenses. The allowed-tools grant 'Bash(infsh *)' enabling arbitrary CLI execution once installed. (location: SKILL.md:16)
description injection
The YAML frontmatter description is heavily keyword-stuffed with broad trigger phrases ('inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok') designed to hijack agent tool selection for a wide range of AI-related queries, funneling them through this impersonator's skill. (location: SKILL.md:3 (description field in YAML frontmatter))
curl https://api.brin.sh/skill/inference-sh-0%2Fskills%2Fagent-toolsCommon questions teams ask before deciding whether to use this skill in agent workflows.
inference-sh-0/skills/agent-tools currently scores 26/100 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.