Security audit

Aha Skills Finder

Security checks for vulnerabilities and agentic risk

Overview

The available evidence points to a coherent research/discovery-oriented skill with no malware detections or artifact-backed signs of hidden, destructive, or credential-stealing behavior.

This looks safe to install based on the supplied telemetry, but review the skill’s discovery behavior if you are sensitive to broad search expansion or unintended language/region assumptions. It should not be treated as granting credential, mutation, or background authority unless the installed package contains additional files not reflected here.

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 (2)

Natural-Language Policy Violations

Low

Confidence: 76% confidence
Finding: The contract explicitly requires or encourages inclusion of "local-language terms" in query expansion fields. This introduces a locale-specific behavior in the skill specification, but the document does not state that the user can opt in to language selection or that the locale constraint is justified as region-specific.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: This manifest includes trigger-like discovery phrases such as 'best Codex skills', 'recommended Claude skills', and similar query branches without narrowing when they should or should not be used. Because the file is a manifest and the examples are broad, recommendation-oriented phrases could collide with ordinary user requests and cause overbroad source expansion behavior.

Static analysis

No suspicious patterns detected.