context safety score
A score of 49/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
shadow chaining
SKILL.md references 1 external package/skill installation(s)
description injection
SKILL.md lines 12-14 instruct the agent to invoke 'Web_Search' tool with specific parameters ('set the Search Type to videos and prefer official YouTube links'). A music downloader skill should describe its own capabilities, not direct the agent to call other tools in its environment. This is agent behavioral manipulation embedded in the skill description. (location: SKILL.md:12-14)
credential exposure
Command template includes --username 'YOUR_YOUTUBE_EMAIL' --password 'YOUR_PASSWORD' passed as plaintext CLI arguments. An agent following this template may prompt users for credentials and pass them insecurely via command line, where they could be logged in shell history or process listings. (location: SKILL.md:192)
supply chain
Extreme mismatch between install count (7.69M) and engagement (5 stars, 0 forks, 1 contributor, not listed on registry). This pattern is consistent with inflated install counts to manufacture trust. The skill_description field contains HTML meta tag content ('width=device-width, initial-scale=1') rather than an actual description, suggesting metadata was scraped or fabricated. No license. Single contributor on a personal account. (location: metadata.json)
curl https://api.brin.sh/skill/nymbo%2Fskills%2Fmusic-downloaderCommon questions teams ask before deciding whether to use this skill in agent workflows.
nymbo/skills/music-downloader currently scores 49/100 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.