Security audit

AANA Decision Log Skill

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill is a coherent decision-log template that emphasizes truthful, redacted audit notes and does not request code execution, persistence, or broad data access.

Installers should treat this as a logging aid, not a compliance checker. Use it with redacted summaries and avoid placing secrets, full records, or unsupported verification claims in generated decision logs.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This is a JSON schema file, so SQP-1 applies. The "trigger" property only specifies that the value is a non-empty string, with no enumeration, pattern, scope constraint, or negative examples to prevent vague trigger phrases such as everyday language from being recorded or accepted.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.