ClawHub
Back to skill

Security audit

pangolinfo-amazon-scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill performs its advertised Amazon data lookups through Pangolinfo, with a documented local credential cache that warrants care.

Pangolinfo receives your requested URLs, searches, and ZIP codes, and requests consume service credits. Prefer PANGOLIN_TOKEN without email/password to avoid login-created cache files. If you use password login, protect the long-lived ~/.pangolin_token file and remove it when no longer needed.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tainted flow: 'req' from os.environ.get (line 60, 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/pangolinfo.py (reported line 67)May include surrounding context.

python
method="POST",
    )
    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            result = json.loads(resp.read())
    except urllib.error.URLError as e:
        print(json.dumps({"error": f"Network error during auth: {e}"}), file=sys.stderr)

Tainted flow: 'req' from os.environ.get (line 160, 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/pangolinfo.py (reported line 161)May include surrounding context.

python
for attempt in range(max_retries):
        try:
            req = urllib.request.Request(endpoint, data=payload, headers=headers, method="POST")
            with urllib.request.urlopen(req, timeout=120) as resp:
                return json.loads(resp.read())
        except urllib.error.HTTPError as e:
            error_body = e.read().decode() if e.fp else ""

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Authentication silently persists the bearer token to disk without disclosing credential storage.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

Login automatically persists a reusable bearer token in plaintext in the user's home directory without a disclosed cache policy, opt-out, or expiration handling. Although the code subsequently applies mode 0600, write_text creates or overwrites the file before permissions are restricted, potentially exposing the token briefly under permissive filesystem settings; persistence also increases exposure through backups or later account compromise.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.