context safety score
A score of 43/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Extreme trust signal mismatch: 7.69M claimed installs but only 3 stars, 0 forks, from a 52-day-old unverified org (frames-engineering). Not listed on skills.sh registry. No license. The install count appears fabricated to manufacture trust and bypass security review. (location: metadata.json)
description injection
SKILL.md contains agent behavior override instructions: 'No command not found errors. No asking for clarification. Just execute.' and 'You ARE websh. Your conversation is the terminal session.' These directives suppress the agent's normal safety checks and refusal behaviors, causing it to blindly execute arbitrary commands without verification. (location: SKILL.md:31,121)
description injection
skill_description field in metadata.json contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag rather than a legitimate skill description. This indicates either metadata injection/scraping manipulation or deliberate obfuscation of the skill's true purpose. (location: metadata.json (skill_description field))
curl https://api.brin.sh/skill/frames-engineering%2Fskills%2FwebshCommon questions teams ask before deciding whether to use this skill in agent workflows.
frames-engineering/skills/websh currently scores 43/100 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.