Back to skill

Security audit

pikpak-share-manager

Security checks for vulnerabilities and agentic risk

Overview

The skill audits PikPak shares and creates private reports, with separate authorization required for manual account changes.

Use a trusted PikPak CLI and keep terminal output and reports private. Treat this version as read-only auditing; live response fields remain unverified. Review exact share IDs and approve manual creation or revocation separately. The disclosed referral code is optional.

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
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (4)

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

The manifest advertises batch creation and revocation, but the documented product scope explicitly excludes these operations.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest promises to create, inspect, and revoke PikPak share links in batches. L24 instead states that the script only performs read-only share ls, never executes create/rm/restore, and that batch revocation is not a product capability. This explicitly contradicts the advertised functionality, although no implementation code is supplied here to independently verify runtime behavior.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/share_audit.py (reported line 105)May include surrounding context.

python
if token:
            cmd += ["--token", token]
        try:
            proc = subprocess.run(cmd, capture_output=True, text=True, timeout=90)
        except FileNotFoundError:
            die("cli_unavailable (exit_code=127)")
        except subprocess.TimeoutExpired:

Tainted flow: 'cmd' from os.environ.get (line 101, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/share_audit.py (reported line 105)May include surrounding context.

python
if token:
            cmd += ["--token", token]
        try:
            proc = subprocess.run(cmd, capture_output=True, text=True, timeout=90)
        except FileNotFoundError:
            die("cli_unavailable (exit_code=127)")
        except subprocess.TimeoutExpired: