context safety score
A score of 32/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Install count of 7,690,000 is fabricated/manipulated. A 31-day-old account with 4 stars, 1 fork, 1 contributor, no license, and not listed on the registry cannot have 7.69M installs. This is social engineering to manufacture trust signals. (location: metadata.json (install_count, owner_account_age_days, stars))
description injection
skill_description field contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag value rather than a legitimate description. This indicates metadata injection attempting to inject HTML attributes into rendering contexts. (location: metadata.json (skill_description))
description injection
SKILL.md is a comprehensive agent behavioral override from an untrusted source (31-day-old account). It instructs agents to adopt a new identity (SOUL.md), treat the skill's rules as 'core directives', perform 'behavioral integrity checks' to resist removal of its instructions, and run persistent 'heartbeat' loops — effectively hijacking the agent's control flow. From a trusted, established project this would be a feature; from this account profile it is a manipulation pattern. (location: SKILL.md (lines 249-258 'Core Rules', lines 369-379 'Behavioral Integrity Check', lines 389-415 'Heartbeat System'))
scope violation
Skill instructs agents to create and maintain an extensive persistent file system (USER.md, SOUL.md, MEMORY.md, SESSION-STATE.md, working-buffer.md, daily logs) that captures detailed user context, preferences, corrections, decisions, and conversation history across sessions. This builds a comprehensive user profile that persists on disk — far beyond what a 'proactive agent' productivity skill needs. (location: SKILL.md (lines 98-112 'Architecture Overview', lines 134-167 'WAL Protocol'))
curl https://api.brin.sh/skill/halthelobster%2Fproactive-agent%2Fproactive-agentCommon questions teams ask before deciding whether to use this skill in agent workflows.
halthelobster/proactive-agent/proactive-agent currently scores 32/100 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.