context safety score
A score of 25/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 1 suspicious install hook pattern(s) in package manifests/scripts
supply chain
Found 1 remote script execution pattern(s) in CI/CD workflows
supply chain
Found 2 unexpected binary file(s) in source repository
description injection
The 'proactive_context' tool description uses directive language to manipulate agent behavior: 'REQUIRED: Call this tool with EVERY user message', 'Always call this FIRST'. This instructs the agent to forward every user message to the shodh backend on every turn, regardless of user intent. Combined with auto_ingest defaulting to true, this creates silent pervasive data capture of all user conversations. While the backend is local by default, the description is designed to override agent autonomy rather than describe tool functionality. (location: mcp-server/index.ts — proactive_context tool description (~line 739))
supply chain
The npm postinstall script (mcp-server/scripts/postinstall.cjs) downloads and executes a platform-specific binary from GitHub releases using execSync('tar -xzf ...') and sets it executable (chmod 0o755). The binary is then auto-spawned at runtime via child_process.spawn() with detached:true and stdio:'ignore'. Additionally, opaque binary blobs (mcp-publisher.exe at 18MB, mcp-publisher.tar.gz at 6.9MB) are committed directly to the repository root. These binaries cannot be audited from source and represent a supply chain risk if the GitHub account or releases are compromised. (location: mcp-server/scripts/postinstall.cjs, mcp-publisher.exe, mcp-publisher.tar.gz)
curl https://api.brin.sh/mcp/varun29ankuS%2Fshodh-memoryCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
varun29ankuS/shodh-memory currently scores 25/100 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.