Back to skill

Security audit

Perpulator

Security checks for vulnerabilities and agentic risk

Overview

This API-backed trading analysis skill is mostly coherent, but it unnecessarily prints the user's API key and uses an unsafe shell-command pattern for user-supplied trade inputs.

Review before installing. The skill's external API use is disclosed and aligned with its purpose, but do not run it where API keys may be logged; the key check should be changed to test presence without printing the value, and request payloads should be built with validation and safe JSON serialization.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:21
Finding

Perpulator API Key Exposed in Terminal Output and Execution Logs

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:56
Finding

Potential Shell Command Injection Through Unsafe User-Value Substitution

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to read PERPULATOR_API_KEY from the environment and then use it in an outbound request, but it does not require clear user consent or provide a user-facing warning before accessing credentials and making a network call. In an agent setting, silent credential access plus transmission to an external service creates a real secret-handling risk, especially if users are unaware the skill will inspect environment variables and contact a third-party endpoint.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill directs the agent to send user-supplied trading data plus an authorization bearer token to an external API via curl. Although external API use is core to the skill's function, the instruction is still security-relevant because it normalizes transmission of potentially sensitive account/trading intent data and a credential to a third-party service without an explicit consent gate or trust boundary warning.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

md
## Step 3 — Call the Perpulator API

Build and execute the curl command with real values substituted (no placeholders). Always include `X-Perpulator-Client: perpulator/1.0` so the server can identify this as a Perpulator skill request.

Example for BTC long at 71000, size 1000, 10x, SL 65000, TP 82000: