context safety score
A score of 31/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
github api error
Could not fetch GitHub metadata: GitHub API returned 404: {"message":"Not Found","documentation_url":"https://docs.github.com/rest/repos/repos#get-a-repository","status":"404"}
scope violation
SKILL.md is completely empty (0 bytes) yet the skill is named 'agent-memory' and claims 1200 installs. A skill with zero content, zero documentation, and no tool definitions provides no legitimate functionality. Combined with empty owner/repo fields, no license, 0 stars, and unknown account age, this appears to be a placeholder or squatted skill name with no verifiable purpose. (location: SKILL.md)
description injection
The skill_description field contains 'width=device-width, initial-scale=1' — an HTML meta viewport tag value, not a legitimate skill description. This is either a scraping artifact from a malicious or broken source page, or nonsensical data injected into the description field. In rendering contexts that interpret HTML, this could contribute to content injection. (location: metadata.json:skill_description)
typosquat
The name 'agent-memory' is a highly generic, desirable name in the AI agent ecosystem. Combined with zero trust signals (0 stars, 0 contributors, empty owner/repo, no license, not listed on registry, unverified), empty SKILL.md, and a nonsensical description, this appears to be name-squatting on a common agent capability concept rather than a legitimate skill offering. (location: metadata.json:skill_name)
curl https://api.brin.sh/skill/api%2Fgit%2Fagent-memoryCommon questions teams ask before deciding whether to use this skill in agent workflows.
api/git/agent-memory currently scores 31/100 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.