Security audit
Security checks for vulnerabilities and agentic risk
This Feishu Sheets skill is coherent and not deceptive, but it can immediately delete or modify remote spreadsheet data without documented confirmations or safety checks.
Install only if you are comfortable giving an agent Feishu app credentials that can read, write, create, and delete spreadsheet content. Before using delete actions, verify the spreadsheet token, sheet ID, and ranges manually, and keep a backup or recovery path for important sheets.
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
Without declared permissions the skill's intent is opaque and cannot be validated.
The skill documents destructive actions such as deleting rows, columns, and worksheets without any warning, confirmation guidance, backup advice, or scoping safeguards. In an agent setting, this increases the chance of accidental or prompt-induced irreversible data loss because users or downstream agents may invoke these operations without understanding that they are destructive.
This markdown file describes delete operations for rows/columns and worksheets, which can affect user data, but it does not include any warning about data loss, irreversibility, or the need to confirm the target resource before execution. Under the markdown-specific SQP-2 criteria, destructive behaviours that could affect user data should be accompanied by warnings.
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
})
This code reads FEISHU_APP_ID and FEISHU_APP_SECRET from environment variables and sends them in an HTTP request to obtain an access token. While this is functionally expected for authentication, the file provides no user-facing print, confirmation, or explicit warning that credentials from the environment will be used and transmitted.
The CLI exposes destructive operations such as delete_dimension and delete_sheet and executes them immediately based solely on command-line arguments, with no confirmation, dry-run mode, or guardrails. In an agent/tooling context, this increases the risk of accidental or prompt-induced destructive changes to user spreadsheets, especially because the skill is explicitly designed to modify remote data.
No suspicious patterns detected.