context safety score
A score of 49/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 3 secret pattern match(es) in repository files
typosquat
Repository owner 'anthropics' closely mimics Anthropic's official GitHub organization 'anthropic' (extra trailing 's'). Combined with the repo name 'claude-plugins-official' using 'official' to assert authority, this appears designed to impersonate Anthropic's official Claude tooling. Despite org_verified being true and high install counts, the pattern of impersonating a well-known AI company's namespace is a strong typosquatting signal. (location: metadata.json: full_name 'anthropics/claude-plugins-official')
description injection
The skill_description field contains 'width=device-width, initial-scale=1' — an HTML meta viewport tag value, not a legitimate skill description. This content could be an injection attempt targeting contexts where the description is rendered into HTML, potentially enabling HTML/attribute injection depending on how downstream systems template the description field. (location: metadata.json: skill_description field)
scope violation
SKILL.md is completely empty (0 lines) despite the skill claiming 7.69M installs and 8.4K stars. A legitimate popular skill would document its capabilities. An empty SKILL.md means agents have no documented contract of what this skill does, making it impossible to verify scope compliance. Combined with the suspicious description field and typosquatting indicators, this suggests the skill is not what it claims to be. (location: SKILL.md)
curl https://api.brin.sh/skill/anthropics%2Fclaude-plugins-official%2FplaygroundCommon questions teams ask before deciding whether to use this skill in agent workflows.
anthropics/claude-plugins-official/playground currently scores 49/100 with a suspicious verdict and medium 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.