context safety score
A score of 47/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
typosquat
Skill named 'sync' in repo 'agent-plugins' with 0 stars, 0 forks, no license, not listed on registry, unverified org, yet claims 7.69M installs. The extremely generic name 'sync' in a repo called 'agent-plugins' appears designed to squat on a high-value name to intercept agent tool searches. The massive install count with zero community engagement (0 stars/forks) is a strong indicator of artificial inflation or count manipulation. (location: metadata.json)
description injection
The skill_description field contains 'width=device-width, initial-scale=1' which is an HTML viewport meta tag value, not a legitimate skill description. This suggests the skill metadata was either scraped from an HTML page to impersonate another project, or is an attempt to inject HTML/rendering directives into contexts where the description is displayed. An empty SKILL.md combined with this nonsensical description means the skill provides no honest documentation of its capabilities. (location: metadata.json: skill_description field)
scope violation
SKILL.md is completely empty — the skill documents zero capabilities, zero parameters, and zero usage instructions. A skill with no documentation provides no contract about what it does, making it impossible for an agent to give informed consent. Any behavior the skill exhibits is undisclosed by definition, constituting a scope violation since nothing is in scope. (location: SKILL.md)
curl https://api.brin.sh/skill/october-academy%2Fagent-plugins%2FsyncCommon questions teams ask before deciding whether to use this skill in agent workflows.
october-academy/agent-plugins/sync currently scores 47/100 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.