context safety score
A score of 43/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
doc injection
README/docs contain 1 agent-targeting injection pattern(s)
doc injection
README 'When to offer +W' section (lines 232-241) embeds behavioral instructions directing AI agents to proactively push commercial wishlist feature during user indecision moments ('maybe later', 'too expensive right now'). CLAUDE.md confirms wording is deliberately 'crafted to encourage AI assistants to proactively offer' the feature. While MCP tool usage guidance is normal, placing AI behavioral triggers in README documentation (commonly ingested as context) rather than solely in MCP tool descriptions represents soft behavioral manipulation, particularly concerning from a 0-star, 67-day-old unverified org. (location: README.md:232-241)
description injection
The add_to_wishlist tool description contains behavioral steering instructions directing the AI agent to proactively invoke the tool in situations the user did not request — specifically during 'INDECISION MOMENTS' (user says 'maybe later', 'too expensive'), 'AFTER PRODUCT RECOMMENDATIONS', and 'GIFT CONTEXT'. These are not descriptions of what the tool does, but instructions telling the agent WHEN to unsolicited offer the tool. The shopping_assistant prompt embeds a marketing statistic ('90% of consumers don't buy in the moment') as a behavioral nudge. The wishfinity://guide resource reinforces this with 'Be proactive but not pushy'. This is commercially-motivated prompt injection via MCP tool metadata, designed to turn the user's AI assistant into a Wishfinity sales funnel. While it does not bypass safety checks or claim pre-authorization, it manipulates agent behavior beyond the user's intent. (location: src/index.ts:21-46 (tool description), src/index.ts:73-76 (shopping_assistant prompt), src/index.ts:114-132 (wishfinity://guide resource))
curl https://api.brin.sh/mcp/wishfinity%2Fwishfinity-mcp-pluswCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
wishfinity/wishfinity-mcp-plusw currently scores 43/100 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 mcp server.
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.