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)
typosquat
Repository owner 'inference-sh-0' is a 13-day-old unverified org with a name designed to impersonate legitimate 'inference-sh' or similar inference platforms. The '-0' suffix is a classic typosquat variant. Combined with 55 stars but a claimed 7.69M installs (heavily inflated), no license, and not listed on the registry, this is a textbook squatting pattern on the high-value 'agent-browser' skill name. (location: metadata.json: owner='inference-sh-0', owner_account_age_days=13, org_verified=false)
scope violation
SKILL.md is completely empty (0 lines) while claiming to be 'agent-browser' with 7.69M installs. A legitimate browser automation skill would document its tools, parameters, and capabilities. An empty skill file with a popular name is characteristic of a placeholder/squatting package that could be updated later with malicious content (starjacking/install count inflation followed by payload delivery). (location: SKILL.md (empty file))
supply chain
The skill_description field contains 'width=device-width, initial-scale=1' which is an HTML viewport meta tag, not a legitimate skill description. This suggests the metadata was either injected with garbage data or scraped from an HTML page — indicating the skill metadata is fabricated rather than authored. Combined with the 13-day-old account and empty SKILL.md, this points to an automated squatting operation. (location: metadata.json: skill_description='width=device-width, initial-scale=1')
curl https://api.brin.sh/skill/inference-sh-0%2Fskills%2Fagent-browserCommon questions teams ask before deciding whether to use this skill in agent workflows.
inference-sh-0/skills/agent-browser 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.