First Seen
Feb 19, 2026
Last Scanned
Feb 22, 2026
Findings
5
Score
62/100
Findings (5)
Detects skills that both read sensitive credential files and send data to external services
access to a separate private key + Send transactions to addresses from external Block access to git credentials, SSH keys, and repository tokens. If git operations are needed, use scoped deploy keys and restrict the tool to specific repositories.
Likely FP if the match is documentation about git configuration (e.g., setting up git credentials helper) rather than code that reads and transmits them.
Detects loading of prompt templates or agent instructions from remote URLs at runtime
instruction
Source: https:// Avoid loading and running third-party plugins or extensions at runtime without integrity verification. Implement code signing, checksum verification, and sandboxing for dynamically loaded code.
Likely FP if the third-party content is a well-known, established plugin loaded from a verified marketplace with code signing.
Detects patterns where credential or secret reads are combined with external data transmission
access to a separate private key + upload content Prevent credentials and sensitive data obtained by one MCP tool from being passed to other tools. Implement data isolation between tools and restrict cross-tool data flow for secrets.
Likely FP if the cross-tool data flow is intentional API authentication (e.g., a tool fetches an auth token that another tool uses for the same service).
Detects patterns where external API responses are used directly without validation or sanitization
API response + IMMEDIATELY STOP and ALERT USE Validate and sanitize all data received from external APIs before using it in tool operations or agent prompts. Implement schema validation and treat API responses as untrusted input.
Likely FP if the match is a truncated table cell or documentation fragment that mentions API responses in a descriptive context, not actual unvalidated data processing.
Detects URLs fetched at runtime that control or influence agent behavior without pinning
GET `https:// + Rules Avoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.
Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.