context safety score
A score of 46/100 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 20 external package/skill installation(s)
shadow chaining
The skill's entire purpose is to get agents to install 13+ additional skills from the same publisher (inference-sh/skills) via npx skills add commands. It acts as a bootstrapper that expands the attack surface by loading more skills into the agent. The allowed-tools wildcard Bash(npx skills *) enables arbitrary skill installation. An agent invoking this skill will be prompted to install numerous additional skills, each adding new tool permissions. (location: SKILL.md:1-122)
scope violation
The skill is named 'related-skill' suggesting it finds skills related to a user's needs, but the content is a hardcoded catalog exclusively promoting skills from the same publisher (inference-sh/skills). It does not actually discover or evaluate related skills — it is a self-promotional installer disguised as a discovery tool. (location: SKILL.md:1-6)
supply chain
Extreme discrepancy between install count (7.69M) and GitHub stars (61). Legitimate packages with millions of installs typically have thousands of stars. Combined with: not listed on skills.sh registry, organization not verified, no license, and only 1 contributor — this suggests inflated install metrics that could mislead trust assessments. (location: metadata.json:1)
description injection
The description contains an unusually broad set of trigger phrases ('related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions') designed to activate this skill on a wide range of agent queries, maximizing the chance an agent will invoke it and subsequently be led to install additional skills from the same publisher. (location: SKILL.md:3)
curl https://api.brin.sh/skill/inference-sh%2Fskills%2Frelated-skillCommon questions teams ask before deciding whether to use this skill in agent workflows.
inference-sh/skills/related-skill currently scores 46/100 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.