Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to be a Feishu Sheets integration, but its delete actions can remove spreadsheet content without a built-in confirmation step.
Install only if you trust it to modify Feishu spreadsheets. Use least-privileged Feishu app credentials, limit spreadsheet access, preview the target sheet or range first, and require explicit confirmation before delete_dimension or delete_sheet actions.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
All API calls require a tenant access token in the Authorization header:
Authorization: Bearer {tenant_access_token}
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
### 7. Delete Rows/Columns
**Endpoint:** `DELETE /sheets/v2/spreadsheets/{spreadsheet_token}/dimension_range`
**Request Body:** Same as insert
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
self._token = None
def _get_token(self) -> str:
"""Get tenant access token"""
if self._token:
return self._token
The skill exposes capabilities that can access external services and potentially environment-backed credentials, but it does not declare any explicit tool scope such as allowed-tools or permissions boundaries for the agent runtime. In a security-sensitive integration, this can lead to overly broad tool use, unclear privilege boundaries, and accidental misuse of networked functionality beyond what the skill documentation narrowly describes.
The skill documents destructive actions such as delete_dimension and delete_sheet without requiring confirmation, warning about irreversible effects, or recommending preview/safeguard flows. In the context of a spreadsheet-management skill, this materially increases the chance of accidental or socially engineered data loss because the skill is specifically designed to modify and delete user content.
This markdown file documents deletion operations for rows/columns and worksheets, which can affect user data and system integrity. The description provides endpoints and request bodies but does not include any warning, caution, or note that these operations may permanently remove spreadsheet content.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
if self._token:
return self._token
resp = requests.post(AUTH_API, json={
"app_id": self.app_id,
"app_secret": self.app_secret
})
The code performs a destructive delete operation against spreadsheet dimensions via the Feishu API, but provides no confirmation prompt or user-facing warning before removing rows or columns. Although the method has an internal docstring, the CLI path exposes this irreversible action without any disclosure to the user at invocation time.
This method deletes an entire worksheet through the remote API, which is a destructive operation affecting user data. The implementation does not include a confirmation prompt, warning message, or other user disclosure beyond an internal docstring.