T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:24- Finding
Private-message access and automated replies occur without explicit authorization
- Content
View full analysis
- Remediation
View remediation
Security audit
Agenticflow Skill
Security checks for vulnerabilities and agentic risk
Overview
This skill describes broad LinkedIn automation, including automatic private-message reading and replies, without clear separate user approval or destination controls.
Install only if you are comfortable granting broad LinkedIn account automation. Before use, require separate opt-in controls for posting, private-message reading, message sending, contact management, analytics, and daily summaries; confirm recipients and final message text before anything is sent.
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
- 93% confidence
- Finding
The skill explicitly automates processing of unread private LinkedIn messages and sends daily summaries to a channel or by email, but it does not describe consent, minimization, retention, or protections for personal and potentially sensitive content. In this context, automated collection, analysis, and onward sharing of private communications can expose confidential data and create privacy, compliance, and unauthorized-disclosure risks.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The manifest description and operational instructions are entirely in French, and the file does not indicate that the user can choose another language or that the skill is intentionally limited to a French-speaking context. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.
- Content