context safety score
A score of 32/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 12 secret pattern match(es) in repository files
supply chain
Found 5 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 5 remote script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 18 unexpected binary file(s) in source repository
typosquat
Repository owner 'personamanagmentlayer' is a misspelling of 'persona management layer' (missing 'e' in management). Combined with a 44-day-old unverified org account, 5 stars, 1 contributor, and an empty SKILL.md, this appears to be a deceptive identity designed to impersonate a legitimate concept or project. (location: metadata.json: owner field)
scope violation
SKILL.md is completely empty (0 lines) yet the skill is named 'finance-expert'. There is no tool definition, no capability description, no parameters — the skill provides zero functionality. This is a hollow shell that exists only as a registry entry with a fabricated install count of 7.69M (impossible for a 44-day-old repo with 5 stars). The skill_description field contains 'width=device-width, initial-scale=1' which is HTML viewport metadata, not a skill description — suggesting either injection into the registry metadata or a broken/malicious scraping artifact. (location: SKILL.md (empty), metadata.json: skill_description and install_count)
description injection
The skill_description field in metadata contains 'width=device-width, initial-scale=1' — an HTML meta viewport attribute value rather than a legitimate description. While this alone may not directly manipulate an agent, it indicates the metadata was either injected or scraped from a deceptive HTML page designed to populate registry fields with non-description content, which could be a vector for more sophisticated injection in future versions. (location: metadata.json: skill_description)
curl https://api.brin.sh/skill/personamanagmentlayer%2Fpcl%2Ffinance-expertCommon questions teams ask before deciding whether to use this skill in agent workflows.
personamanagmentlayer/pcl/finance-expert 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.