context safety score
A score of 35/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 1 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 3 unexpected binary file(s) in source repository
supply chain
README documents that npm postinstall hook automatically copies skill files into the host project directory (line 39: 'postinstall will attempt to copy skills into the host project', referencing install-skills.mjs). Automatic file writing into consuming projects via postinstall is a supply chain concern, particularly from a 197-day-old personal account without org verification. The actual package.json and install-skills.mjs were not available for inspection to verify the scope of files being written. (location: README.md:39,49)
typosquat
Repository 'ailabs-393/ai-labs-claude-skills' uses 'claude-skills' and 'ai-labs' in its naming to impersonate an official Anthropic/Claude skill. Owner 'ailabs-393' is a 197-day-old personal account with a numeric suffix suggesting a squatted identity. Not org-verified. (location: metadata.json (full_name, owner))
scope violation
SKILL.md is completely empty (0 bytes) — the skill provides zero documentation of what it actually does. A skill named 'research-paper-writer' with no description, no tool definitions, and no parameter documentation means agents have no way to know what capabilities they are granting. The skill_description field contains 'width=device-width, initial-scale=1' which is an HTML viewport meta tag, not a skill description — indicating scraped/garbage metadata. (location: SKILL.md, metadata.json (skill_description))
supply chain
Install count of 7.69M is highly inconsistent with 315 stars, 2 contributors, 197-day-old account, not listed on registry, and not org-verified. This pattern strongly suggests artificially inflated install counts to manufacture trust signals, a common supply chain attack vector to encourage adoption of malicious packages. (location: metadata.json (install_count, stars, owner_account_age_days, listed_on_registry))
curl https://api.brin.sh/skill/ailabs-393%2Fai-labs-claude-skills%2Fresearch-paper-writerCommon questions teams ask before deciding whether to use this skill in agent workflows.
ailabs-393/ai-labs-claude-skills/research-paper-writer currently scores 35/100 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.