T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:20- Finding
Overbroad Modification of Files Outside the Intended Output Package
- Content
View full analysis
- Remediation
View remediation
Security audit
TRPG Convert to Briefing Package
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly a TRPG conversion helper, but it tells agents to modify active source files outside the intended briefing package without clear limits or user approval.
Review this skill before installing if your project contains authoritative rulebooks, scenarios, or character sheets outside briefing_package. Use it only in a version-controlled workspace or instruct the agent to treat source files outside briefing_package as read-only unless you approve a precise file list and diff.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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 (1)
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 (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill instructs the agent to modify multiple files in the current folder and even outside the briefing_package without requiring an explicit user confirmation or a clear warning that file writes will occur. In an agent environment, this can cause unintended bulk edits to unrelated or authoritative files, especially because the skill also encourages broad scanning and batch processing across many paths.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
These instructions mandate that all Chinese content must be written in Traditional Chinese and explicitly forbid Simplified Chinese. This is a language/locale policy constraint presented as unconditional behavior, with no opt-in choice for the user and no clear region-specific justification documented in the file.
- Content