Security audit

Classement document

Security checks for vulnerabilities and agentic risk

Overview

This accounting archiving skill matches its stated purpose, but its file handling is too loosely bounded and could copy or write files outside the intended archive if given hostile metadata.

Install only if this skill will run on trusted dossier metadata and under a restricted account whose read/write access is limited to the intended intake and archive folders. Before production use, require safe slug/date validation, reject absolute or parent-directory paths, verify source files are inside an approved intake directory, and enforce the archive boundary before mkdir or copy operations.

A.I.G

Vulnerability Patterns

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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/classer.py:75
Finding: Destination Path Traversal Allows Writes Outside the Client Archive
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: scripts/classer.py:141
Finding: Unrestricted Source Paths Allow Unauthorized Local File Archival
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

Static analysis

No suspicious patterns detected.