context safety score
A score of 26/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 64 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 64 remote script pattern(s) in documentation (likely install instructions, not executable)
typosquat
Organization 'inference-sh-9' is 3 days old, unverified, with 1 contributor, but all README branding, links, and installation commands reference 'inference-sh/skills' and 'inference.sh'. The '-9' suffix on a brand-new org strongly suggests impersonation of a legitimate 'inference-sh' organization. Users and agents could be deceived into trusting this as the official source. (location: README.md (entire file); metadata.json (owner: inference-sh-9, owner_account_age_days: 3, org_verified: false))
doc injection
README instructs users to install skill files into agent configuration directories (~/.claude/skills/, ~/.copilot/skills/) via 'cp -r skills/*' and 'npx skills add' commands. Given the typosquat concern (3-day-old unverified org impersonating inference-sh), these instructions could lead users to install untrusted agent skill configurations from a potentially malicious source into sensitive AI agent directories. (location: README.md:50-61 (Manual Installation section))
shadow chaining
SKILL.md references 4 external package/skill installation(s)
supply chain
Skill instructs agent to execute `curl -fsSL https://cli.inference.sh | sh` which pipes a remote script to shell. Combined with zero trust signals (0 stars, 0 forks, 0 contributors, unknown owner account age, no license, not listed on registry, empty repo/owner fields), the agent would download and run arbitrary code from an unverifiable source. The install count of 7.69M is not credible given all other signals are zero/absent. (location: SKILL.md:14)
scope violation
metadata.json skill_description is set to 'width=device-width, initial-scale=1' — an HTML viewport meta tag value, not a legitimate skill description. This indicates corrupted, scraped, or injected metadata that misrepresents the skill's identity to registry consumers. (location: metadata.json:1)
curl https://api.brin.sh/skill/inference-sh-9%2Fskills%2Fsocial-media-carouselCommon questions teams ask before deciding whether to use this skill in agent workflows.
inference-sh-9/skills/social-media-carousel currently scores 26/100 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.