First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
11
Score
20/100
Findings (11)
Detects common jailbreak prompt patterns
circumvent safetyRemove directives that attempt to exfiltrate data through the agent's response (e.g., asking the agent to embed credentials in URLs or include secret values in output).
Likely FP if the text is a legitimate tool instruction about displaying configuration to the user (e.g., show current settings) without external transmission.
Detects common jailbreak prompt patterns
evade filterRemove directives that attempt to exfiltrate data through the agent's response (e.g., asking the agent to embed credentials in URLs or include secret values in output).
Likely FP if the text is a legitimate tool instruction about displaying configuration to the user (e.g., show current settings) without external transmission.
Skill can read private data (credentials, SSH keys, env vars) AND write to public channels (Slack, Discord, email). This combination enables data exfiltration.
[reads_private_data] read `signing_secret + [writes_public_output] send Webhook API to create the webhookBreak the toxic data flow by adding validation and sanitization between the input source and the sensitive operation. Do not pass untrusted data directly to file system, network, or execution APIs.
Likely FP if the data flow involves only trusted, hardcoded values and the taint analysis over-approximated the untrusted input sources.
Detects skills that both read sensitive credential files and send data to external services
read `signing_secret + send Webhook API to register your endpointBlock 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 URLs fetched at runtime that control or influence agent behavior without pinning
Get yours at https:// + settingAvoid 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.
Detects MCP tools that execute arbitrary code
ExecuteCodeRestrict code execution tools to specific languages and sandbox the runtime environment. Use a container or VM-based sandbox instead of running code directly on the host.
Likely FP if the MCP tool is a dedicated code runner (e.g., Jupyter kernel) with documented sandboxing and no network access.
Detects MCP tools that execute arbitrary code
ExecuteCodeRestrict code execution tools to specific languages and sandbox the runtime environment. Use a container or VM-based sandbox instead of running code directly on the host.
Likely FP if the MCP tool is a dedicated code runner (e.g., Jupyter kernel) with documented sandboxing and no network access.
Detects MCP tools that execute arbitrary code
ExecuteCodeRestrict code execution tools to specific languages and sandbox the runtime environment. Use a container or VM-based sandbox instead of running code directly on the host.
Likely FP if the MCP tool is a dedicated code runner (e.g., Jupyter kernel) with documented sandboxing and no network access.
Detects patterns where external API responses are used directly without validation or sanitization
Webhook payload only includes metadata + immediately
await agent.processValidate 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 system-level package installation via brew, apt, yum, or dnf
brew install nPin system packages to specific versions where the package manager supports it. Document the exact packages required and prefer containerized environments to avoid system-wide changes.
Likely FP if the match is standard setup documentation listing well-known system packages (e.g., apt install git curl) that are prerequisites.
Detects system-level package installation via brew, apt, yum, or dnf
brew install cPin system packages to specific versions where the package manager supports it. Document the exact packages required and prefer containerized environments to avoid system-wide changes.
Likely FP if the match is standard setup documentation listing well-known system packages (e.g., apt install git curl) that are prerequisites.