atxp-2

Remove directives that force the agent to call specific tools or APIs not required for the skill's stated functionality. Tool calls should be determined by user intent, not embedded directives.

Likely FP if the skill legitimately needs to call other tools as part of its workflow (e.g., a deployment skill that calls git and cloud CLI tools).

Break 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.

Restrict email and messaging API access to user-initiated actions. Prevent automated sending that could exfiltrate data via email body or attachments.

Likely FP if the skill is an email client or messaging tool whose documented purpose is to send messages on behalf of the user.

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).

Restrict email and messaging API access to user-initiated actions. Prevent automated sending that could exfiltrate data via email body or attachments.

Likely FP if the skill is an email client or messaging tool whose documented purpose is to send messages on behalf of the user.