Security audit
Security checks for vulnerabilities and agentic risk
The skill is coherent documentation for IMAP email integration, but it needs Review because it covers broad mailbox reading, monitoring, and irreversible mailbox changes without strong scoping or confirmation guidance.
Install only if you intend to use an agent for IMAP email development. Treat all mailbox reads, IDLE monitoring, delete/expunge, move/rename, and flag changes as sensitive actions requiring explicit user confirmation, and store OAuth tokens or app passwords in a proper secrets mechanism rather than hardcoding them.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
secure: true, auth: { user: 'user@gmail.com', accessToken: 'ya29.xxxx' // OAuth2 access token } });
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
secure: true, auth: { user: 'user@gmail.com', accessToken: 'ya29.xxxx' // OAuth2 access token } });
The trigger scene is broad enough to activate for many generic email-related tasks, including high-risk automation around reading, monitoring, and modifying mailbox content. In an agent setting, overly broad invocation criteria can cause the skill to be selected in contexts the user did not explicitly intend, increasing the chance of unauthorized email access or actions.
The documentation includes destructive operations such as mailbox deletion, message deletion, expunge, move, and rename without prominent warnings, confirmation guidance, or recovery caveats. In an agent-integrated skill, this can normalize irreversible actions and make it easier for an agent or developer to invoke destructive mailbox changes without realizing the consequences.
This markdown file describes irreversible or potentially destructive operations such as deleting messages, expunging messages, and deleting mailboxes, but it does not include any warning about data loss or the need for user confirmation. Under the markdown-specific SQP-2 criteria, skill documentation should disclose behaviors that could affect user data or system integrity.
This markdown file contains multiple connection examples showing pass and accessToken fields for authenticating to external mail providers. While the file explains protocol details, it does not explicitly warn readers not to hardcode or expose real credentials, even though these examples involve sensitive secrets and network connections to third-party services.
This markdown file includes an example that calls messageFlagsAdd(..., ['\\Seen'], ...), which marks messages as read and alters user mailbox state. The surrounding documentation does not warn the user that this example is state-changing, which could surprise someone expecting search-related examples to be read-only.
No suspicious patterns detected.