context safety score
A score of 20/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 24 secret pattern match(es) in repository files
shadow chaining
SKILL.md references 7 external package/skill installation(s)
scope violation
Skill is named 'project-manager' but SKILL.md describes a collection of 11 ML/AI skills (AI engineer, LLM architect, MLOps, data engineer, etc.) with no project management functionality. This name-content mismatch could deceive users and agents expecting a project management tool into installing a broad ML/AI toolkit with API key handling, model serving, and database access capabilities. (location: SKILL.md:1-236 and metadata.json skill_name field)
typosquat
The generic name 'project-manager' on a 255-day-old personal account with 36 stars but claiming 7.69M installs is suspicious. The install count is wildly disproportionate to the repository's actual popularity (36 stars, 3 forks). This suggests either install count manipulation or metadata fabrication to appear as a trusted, established skill. The actual content (ML/AI scripts) has no relation to the 'project-manager' name. (location: metadata.json)
supply chain
The skill_description field in metadata.json contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag value, not a legitimate skill description. This indicates the metadata was either scraped incorrectly from a webpage or deliberately crafted with non-functional metadata, raising questions about the legitimacy of the entire package and its metadata integrity. (location: metadata.json skill_description field)
curl https://api.brin.sh/skill/404kidwiz%2Fclaude-supercode-skills%2Fproject-managerCommon questions teams ask before deciding whether to use this skill in agent workflows.
404kidwiz/claude-supercode-skills/project-manager currently scores 20/100 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.