Security audit

drillr — Power Terminal for Deep Financial Research

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent financial-research purpose, but its documented inline invocation can turn a crafted user question into locally executed Python code.

Review before installing. The safer path is the companion query.py script, invoked with the question as an argument, but the documented inline command should be fixed or avoided. Run only in a sandbox you are comfortable with, and remember that each research question is sent to the drillr.ai public API endpoint.

A.I.G

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

Error

Location: SKILL.md:137
Finding: Arbitrary Python Code Execution Through Unsafe Query Substitution
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: query.py:90
Finding: Denial of Service Through Unbounded SSE Streaming and Response Accumulation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill executes an inline Python script via a shell and performs outbound network access, but it declares no explicit tool scope or permissions metadata. That mismatch is dangerous because callers and policy systems cannot reliably constrain or review the skill’s actual capabilities, increasing the risk of unintended data egress or policy bypass if the skill is invoked in a broader agent environment.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.