Security audit

Whoislookup

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward WHOIS lookup skill that uses network access as advertised, with a resource-use weakness but no hidden persistence or unrelated data access.

Reasonable to install for domain WHOIS lookups. Avoid pointing --server at untrusted or arbitrary hosts, and prefer adding a response-size cap and overall deadline before using it in automated or exposed workflows.

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

Warning

Location: whoislookup.py:23
Finding: Unbounded WHOIS Response Can Cause Memory and CPU Exhaustion
Content: View full analysis
Remediation: View remediation
max_response_size: raise ValueError("WHOIS response exceeds the size limit") data.extend(chunk) return data.decode("utf-8", errors="replace") except Exception as e: return f"Error querying {server}: {e}" ``` ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/whoislookup.py:23
Finding: Unbounded WHOIS Response Can Cause Memory and CPU Exhaustion in Packaged Script
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: This markdown file describes what the skill does and shows example usage, but it does not define any explicit activation phrases, scope limits, or exclusion conditions. In contexts where README text is reused for skill routing or invocation metadata, the broad description 'Domain WHOIS lookup tool' and generic examples could leave activation boundaries underspecified.
Content: No source excerpt is available for this finding.