context safety score
A score of 47/100 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)
shadow chaining
SKILL.md references 5 external package/skill installation(s)
supply chain
Skill instructs agent to execute 'curl -fsSL https://cli.inference.sh | sh' to install an unverifiable CLI binary. The repository has zero stars, zero forks, zero contributors, no license, empty owner/repo fields, unknown account age, and is not listed on any registry. There is no way to verify the provenance or integrity of this binary. The install count of 7.69M is not credible given zero community signals, suggesting fabricated metadata designed to bypass trust checks. (location: SKILL.md:16)
description injection
Frontmatter description (line 3) is heavily keyword-stuffed with 15+ trigger phrases ('perplexity alternative', 'ai research', 'search + llm', etc.) designed to maximize agent invocation surface. Combined with fabricated trust signals and an unverifiable publisher, this broadens the attack surface by making agents invoke this skill for a wide variety of queries. (location: SKILL.md:3)
scope violation
metadata.json skill_description field contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag, not a real skill description. This indicates either metadata scraping manipulation or a broken/spoofed registry entry, further undermining trust in the skill's declared identity and provenance. (location: metadata.json:1)
curl https://api.brin.sh/skill/inference-sh%2Fskills%2Fai-rag-pipelineCommon questions teams ask before deciding whether to use this skill in agent workflows.
inference-sh/skills/ai-rag-pipeline currently scores 47/100 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.