Back to skill

Security audit

Content Repurposer

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real content repurposing tool, but it can read local files and send their contents to MiniMax without clear top-level disclosure or confirmation.

Install only if you are comfortable sending submitted content to MiniMax. Do not use @file with secrets, private documents, credentials, .env files, customer data, or regulated content unless you have reviewed the provider handling and explicitly intend to upload that file.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
scripts/repurpose.py:201
Finding

Undocumented Local File Content Transmission to an External API

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/repurpose.py:39
Finding

Prompt Injection Through Untrusted Source Content

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tainted flow: 'req' from os.environ.get (line 120, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/repurpose.py (reported line 127)May include surrounding context.

python
method="POST"
            )
            
            with urllib.request.urlopen(req, timeout=60) as resp:
                result = json.loads(resp.read().decode("utf-8"))
                return result["choices"][0]["message"]["content"].strip()
        except Exception as e:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises broad, generic repurposing capability without clear trigger boundaries or scoping constraints, which can cause it to activate on a wide range of user content unintentionally. In an agent environment, overly broad activation increases the chance of processing sensitive or irrelevant data and can lead to unnecessary transmission of user-provided material to downstream systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states that it uses the MiniMax API via OpenClaw but does not clearly warn users that their submitted content may be sent to an external service. If users provide confidential business text, drafts, or personal data, the absence of a prominent disclosure can result in unintended data exfiltration to a third-party processor.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/repurpose.py (reported line 29)May include surrounding context.

python
from pathlib import Path

# API configuration
MINIMAX_API_URL = "https://api.minimax.chat/v1/text/chatcompletion_pro"
MINIMAX_API_KEY = os.environ.get("MINIMAX_API_KEY", "")

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script transmits arbitrary user-supplied content, including file contents loaded via @file, to an external API without any explicit consent prompt, warning, or privacy notice. In a skill context, users may unknowingly send sensitive local data, creating confidentiality and compliance risks if secrets, personal data, or proprietary text are repurposed through the remote service.

Content

No source excerpt is available for this finding.