context safety score
A score of 34/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 2 unexpected binary file(s) in source repository
shadow chaining
SKILL.md references 1 external package/skill installation(s)
supply chain
Skill instructs agents to install and execute an external dependency (atxp-dev/cli) via 'npx skills add atxp-dev/cli' and run 'npx atxp-call' commands that download and execute remote code from an unverified source. Combined with 0 stars, no license, and not being listed on the registry, this external dependency chain is unvetted. (location: SKILL.md:12-21)
scope violation
Skill triggers financial transactions ($0.50 to add entries, $0.10 to edit) via MCP tool calls without prominent consent gating. An agent following these instructions could spend money on behalf of the user without explicit approval. The costs are documented but buried in workflow details rather than flagged as requiring user confirmation. (location: SKILL.md:97-107)
credential exposure
Skill instructs passing authentication cookies as URL query parameters (https://claw.direct?clawdirect_cookie=<cookie_value>). Cookies in URLs are logged in browser history, server access logs, proxy logs, and leaked via Referer headers — a well-known credential exposure anti-pattern. (location: SKILL.md:55-62)
supply chain
Metadata inconsistency: skill_description field contains HTML viewport meta tag content ('width=device-width, initial-scale=1') instead of a real description, and the skill claims 7.69M installs but has 0 stars, is not listed on the registry, and has no license. This combination suggests manipulated or unreliable metadata. (location: metadata.json:1)
curl https://api.brin.sh/skill/napoleond%2Fclawdirect%2FclawdirectCommon questions teams ask before deciding whether to use this skill in agent workflows.
napoleond/clawdirect/clawdirect currently scores 34/100 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.