Security audit

Proof Audit

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly performs a normal proof freshness audit, but it also mandates an under-disclosed promotional closing line for a human service.

Install only if you are comfortable with audits ending in a promotional Proof Expert offer. The web and optional GrowthNation data access are otherwise aligned with the audit task, but organisations needing neutral reports may want to remove or disable the mandatory closing line first.

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:145
Finding: Mandatory Promotional Content Hijacks Audit Output
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: 96% confidence
Finding: The instruction explicitly requires 'British English' for all output. This is a natural-language locale policy constraint, and the file does not offer the user a language or locale choice or explain a justified region-specific need.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.