Security audit
Security checks for vulnerabilities and agentic risk
This looks like a real Cloudflare DNS management skill, but it can change or delete live DNS records with an API token and lacks built-in confirmation or clear safety scoping.
Install only if you are comfortable letting the agent operate on Cloudflare DNS records. Use a Cloudflare token restricted to the needed zone and DNS permissions, keep the token out of logs and files, and require the agent to show the current record and exact planned change before any create, update, delete, or DDNS action.
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).
local record_id="$2"
local result
result=$(cf_api DELETE "/zones/$zone_id/dns_records/$record_id")
if echo "$result" | jq -e '.success' >/dev/null 2>&1; then
info "Record deleted successfully"
The skill documents and relies on shell-based operations but does not declare any tool scope, permissions, or allowed-tools metadata. That creates an authorization ambiguity where an agent may invoke shell capabilities more broadly than intended, increasing the chance of unsafe command execution in a DNS-management context.
The skill includes delete and update DNS operations without warning about service disruption, domain hijacking risk, or the need for explicit user confirmation. In practice, destructive DNS changes can break websites, email delivery, or redirect traffic, especially if an agent executes them without a safety checkpoint.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
set -euo pipefail
API_BASE="https://api.cloudflare.com/client/v4"
# Colors for output
RED='\033[0;31m'
The delete command issues a Cloudflare DELETE request and only prints a success message after the record has already been removed. There is no confirmation prompt, dry-run notice, or prior user-facing warning in the script comments or usage text that this operation is destructive.
The setup instructions tell users to export a Cloudflare API token but do not warn that the token is sensitive, should be minimally scoped, and must not be logged, committed, or exposed in shell history. Mishandling these credentials could allow unauthorized DNS modification across the associated zone.
The script reads CF_API_TOKEN from the environment and sends it in an Authorization header for all API calls. Although the header use is technically necessary, the file does not include a warning or explanatory note that the skill will use the token to make authenticated external requests to Cloudflare.
No suspicious patterns detected.