Back to skill

Security audit

POD Benchmark

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because it flags an unpinned optional CLI and sending seller business details to a third party without a clear disclosure; this indicates review-worthy risk, not proof of malicious intent.

Before installing, consider whether you are comfortable with seller business details being sent to POD Benchmark without a clear user-facing disclosure. Avoid the optional unpinned CLI unless you can verify and restrict the package; the report does not establish that it is malicious. The verdict has medium confidence, and analysis was partial because some local references could not be resolved, so the evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
emoji: "👕"
---

<!-- Published by POD Benchmark. Source: skills/podbenchmark/SKILL.md in the POD Benchmark repository. -->

# POD Benchmark

MCP server referenced without pinned version: 'npx podbenchmark'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The optional CLI instruction uses an unpinned npm package, allowing npx to download and execute whichever release is current with the agent's shell permissions. A compromised package or malicious future release could access local files or credentials; this is a supply-chain exposure, not evidence that the current package is malicious.

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 · SKILL.md (reported line 30)May include surrounding context.

CLI, when a shell is easier: npx podbenchmark <command>.

bash
curl -s https://podbenchmark.com/api/v1/tools/compare_product \
  -H 'content-type: application/json' \
  -d '{"canonicalProductId":"bella-canvas-3001","destination":"US","currency":"USD","choices":{"size":"m","color":"black"}}'

Seller business information is sent to POD Benchmark without a user-facing privacy disclosure.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill directs the agent to send seller-provided supplier, pricing or margin, sales-channel, and shop-location information to a third-party service without requiring a user-facing disclosure. These fields serve the requested calculation and do not include credentials, which limits the risk, but the combination can still reveal nonpublic business information; providing it to the assistant does not necessarily imply awareness of onward transmission.

Content

No source excerpt is available for this finding.