context safety score
A score of 34/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 6 secret pattern match(es) in repository files
typosquat
Skill named 'langgraph-code-review' references the well-known LangGraph (LangChain) project but is published by 'existential-birds/beagle' — a 69-day-old unverified org with only 30 stars and 2 contributors. The repo name 'beagle' bears no relation to LangGraph. This appears designed to impersonate or trade on the LangGraph brand to attract installs. (location: metadata.json: skill_name and full_name fields)
description injection
The skill_description field contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag value, not a legitimate skill description. This is either a rendering injection attempt targeting contexts where the description is interpreted as HTML/meta content, or indicates the metadata was scraped/fabricated incorrectly. Either way, this is not a valid skill description and could cause unexpected behavior in agent UIs or registries. (location: metadata.json: skill_description field)
scope violation
SKILL.md is completely empty (0 bytes) while claiming 7.69M installs. A legitimate, widely-used skill would have documentation. Combined with the empty SKILL.md, there is no way to verify what this skill actually does, making it impossible to assess whether its runtime behavior matches its stated purpose. The skill provides zero transparency about its capabilities. (location: SKILL.md)
supply chain
Extreme mismatch between install count (7.69M) and repository signals (30 stars, 5 forks, 2 contributors, 69-day-old unverified org, not listed on registry). Legitimate packages with millions of installs have proportional community engagement. This pattern is consistent with inflated install counts seen in supply chain attacks designed to build false trust. (location: metadata.json: install_count vs stars/owner_account_age_days/listed_on_registry)
curl https://api.brin.sh/skill/existential-birds%2Fbeagle%2Flanggraph-code-reviewCommon questions teams ask before deciding whether to use this skill in agent workflows.
existential-birds/beagle/langgraph-code-review currently scores 34/100 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.