context safety score
A score of 28/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 1 unexpected binary file(s) in source repository
scope violation
SKILL.md references 1 resource access pattern(s) beyond typical scope
credential exposure
Skill instructs agent to collect passwords, credit card numbers (including CVV), and personal data, write them as plaintext JSON to disk (creds.json), and pass them to an external npx package (sensitive-browser). Credentials are written to disk in cleartext before being handed to an unvetted external process. The npm package sensitive-browser has no verifiable relationship to this repo (0 stars, 0 forks, no license, not registry-listed). (location: SKILL.md:26-49 (sensitive data file creation) and SKILL.md:53-58 (npx execution))
supply chain
The skill delegates all sensitive data handling to 'npx sensitive-browser', which downloads and executes an npm package at runtime. The repository has 0 stars, 0 forks, 1 contributor, no license, and is not listed on the skills registry — yet claims 7.69M installs, which is implausible and suggests fabricated metrics. There is no way to verify the npm package is safe or controlled by the same author. (location: SKILL.md:54 and metadata.json (install_count vs stars/forks mismatch))
scope violation
metadata.json skill_description is 'width=device-width, initial-scale=1' — an HTML viewport meta tag, not a legitimate skill description. This indicates the metadata was improperly scraped or deliberately set to a nonsensical value, undermining trust in the skill's provenance and stated purpose. (location: metadata.json:skill_description field)
curl https://api.brin.sh/skill/napoleond%2Fsensitive-browser%2Fsensitive-browserCommon questions teams ask before deciding whether to use this skill in agent workflows.
napoleond/sensitive-browser/sensitive-browser currently scores 28/100 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.