context safety score
A score of 49/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 16 secret pattern match(es) in repository files
supply chain
Found 2 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 2 remote script pattern(s) in documentation (likely install instructions, not executable)
scope violation
SKILL.md is completely empty (0 lines) yet metadata claims 7.69M installs and 29K stars. A legitimate skill with this adoption level would have a substantive skill definition. The empty file means no skill capabilities are defined, making the skill's actual purpose unknowable and the popularity metrics unverifiable against real functionality. (location: SKILL.md)
description injection
The skill_description field in metadata.json contains 'width=device-width, initial-scale=1' — an HTML meta viewport attribute, not a skill description. This appears to be scraped from an HTML page rather than authored as a legitimate skill definition, suggesting the metadata was fabricated or auto-generated from web scraping rather than reflecting a real skill. (location: metadata.json:skill_description)
typosquat
The repository 'wshobson/agents' uses the highly generic name 'agents' which collides with several well-known AI agent repositories and frameworks. Combined with the fact it is not listed on the registry, has an empty SKILL.md, and has a garbled skill_description sourced from HTML meta tags, this suggests the repo may be positioned to intercept searches for legitimate 'agents' projects rather than being a genuine skill. (location: metadata.json:full_name)
curl https://api.brin.sh/skill/wshobson%2Fagents%2Fgitlab-ci-patternsCommon questions teams ask before deciding whether to use this skill in agent workflows.
wshobson/agents/gitlab-ci-patterns currently scores 49/100 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.