ClawHub
Back to skill

Security audit

PDD Price Update

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Pinduoduo price-changing helper with dry-run, confirmation, guardrails, audit logging, and rollback, though it should only be installed by users who intentionally want local browser-based shop automation.

Install this only if you intentionally want an agent to assist with Pinduoduo merchant price changes through your already logged-in Chrome session. Always review the dry-run plan before allowing --execute, avoid --force unless you have manually checked the change, and keep PDD_AUDIT_PATH unset or pointed at a dedicated audit-log file under your own data directory.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose is narrowly scoped to Pinduoduo price updates with dry-run, confirmation, guardrails, audit logging, and rollback, but the analyzed behavior reportedly implements a generic local WebSocket/CDP transport with none of those safety controls. That mismatch is highly dangerous because it can be used to access or drive an already logged-in browser session on localhost under the cover of a benign e-commerce workflow, potentially enabling unauthorized actions, session abuse, or broader local-browser compromise.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill advertises executable behavior involving local environment access, file writes, and network communication, but it does not declare any explicit tool scope or permissions boundaries. This is dangerous because a caller or agent may invoke a skill with broader capabilities than users expect, enabling unintended access to local files, environment data, or network targets without transparent authorization.

Content

No source excerpt is available for this finding.

Internal Network Request

Medium
Category
Server-Side Request Forgery
Confidence
70% confidence
Finding

Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.

Content

Scanner excerpt · scripts/update_price.py (reported line 37)May include surrounding context.

python
"~/.pdd-data/price_audit.jsonl"))

def find_pdd_page(port):
    with urllib.request.urlopen(f"http://localhost:{port}/json", timeout=5) as _r:
        tabs = json.loads(_r.read().decode())
    for t in tabs:
        if t.get("type") == "page" and "mms.pinduoduo.com" in t.get("url", ""):

Tainted flow: 'AUDIT' from os.environ.get (line 33, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
94% confidence
Finding

The audit log path is taken from the PDD_AUDIT_PATH environment variable and then opened for append without validation. If an attacker can influence the environment of the process, they can redirect writes to arbitrary filesystem locations, causing file clobbering, data corruption, or planting content in sensitive files the process can access.

Content

Scanner excerpt · scripts/update_price.py (reported line 183)May include surrounding context.

python
if verified:
                break

        with open(AUDIT, "a") as f:
            f.write(json.dumps({"ts": datetime.datetime.now(datetime.timezone.utc).isoformat(),
                                "goods_id": goods_id, "mode": plan["mode"], "before": cur,
                                "target": targets, "applied": applied, "commit_id": commit_id,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest content is written in Chinese and states the declaration is for the receiving agent's security assessment, but it does not provide an alternative language or indicate that Chinese is optional. This can violate a language/locale policy when users or downstream agents are not given a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The module docstring is entirely written in Chinese and does not indicate any language choice or opt-in. Under the stated policy, natural-language content that imposes a specific language without user choice can be a locale/language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/update_price.py:48