Security audit

Hallucination Guard — 4-Layer AI Fabrication Defense

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent anti-hallucination purpose, but its audit recipes can cause unsafe shell command execution if file paths, branch names, or search text are attacker-controlled.

Review before installing. This skill is not malicious, but use it only if your agent treats all claim-derived paths, branch names, and text as untrusted and verifies them with structured file/git tools or safely separated command arguments instead of copying the shown shell templates directly.

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 (3)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:50
Finding: Shell Command Injection Through Unquoted Verification Placeholders
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: references/audit-prompt.md:44
Finding: Shell Command Injection in Data Audit Source Path
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: references/drift-monitor.md:43
Finding: Shell Command Injection in Drift-Monitor Artifact Checks
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The natural-language guidance prescribes preferred models and says to default to the cheapest model, but SQP-3 only covers natural-language policy violations such as forced language or locale constraints. This section does not impose a language or locale, so no clear policy violation is present.
Content: No source excerpt is available for this finding.