context safety score
A score of 46/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 84 secret pattern match(es) in repository files
supply chain
Found 12 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 12 remote script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 4 unexpected binary file(s) in source repository
shadow chaining
SKILL.md references 1 external package/skill installation(s)
scope violation
SKILL.md instructs cloning from github.com/fractalmind-ai/agent-manager-skill.git but the skill is published under sickn33/antigravity-awesome-skills. The skill redirects users to install code from a completely different GitHub organization than the publisher, which could serve as a supply chain vector if the fractalmind-ai repo contains different code than what was reviewed. (location: SKILL.md:25)
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 either corrupted/scraped metadata or an attempt to inject HTML attributes through metadata fields that may be rendered in a registry or agent UI. (location: metadata.json:1 (skill_description field))
typosquat
Repository named 'antigravity-awesome-skills' follows the popular 'awesome-*' curated list naming convention, potentially to appear as a well-known community resource. Combined with the mismatch between publisher identity (sickn33) and the actual code source (fractalmind-ai), this raises questions about whether the listing is attempting to ride on the credibility of established awesome-list patterns. (location: metadata.json:1 (repo field))
curl https://api.brin.sh/skill/sickn33%2Fantigravity-awesome-skills%2Fagent-manager-skillCommon questions teams ask before deciding whether to use this skill in agent workflows.
sickn33/antigravity-awesome-skills/agent-manager-skill currently scores 46/100 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.