T06 · System Persistence
Error
- Location
SKILL.md:87- Finding
Recurring Autonomous Social-Media Posting Creates Cross-Session Persistence
- Content
View full analysis
- Remediation
View remediation
Security audit
Social Media Agent
Security checks for vulnerabilities and agentic risk
Overview
This skill is coherent for social media automation, but it can publish and schedule real X/Twitter activity with persistent cron jobs and weak user-control boundaries.
Review before installing. Use this only if you intentionally want an agent to operate an authenticated X/Twitter account. Prefer draft-only workflows unless you explicitly approve each post, reply, quote, and cron schedule, and make sure you know how to list and remove any scheduled jobs it creates.
Vulnerability Patterns
- System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
Findings (2)
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly supports autonomous posting, engagement, cron-based scheduling, and persistent file/memory logging, but it does not present strong user-facing warnings or mandatory confirmation checkpoints before performing account actions. Because it targets a real social media account through browser automation, misuse or accidental execution could result in unauthorized posts, reputation damage, and long-lived automated behavior that continues after the initial interaction.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger description is broad enough to activate on generic requests about tweets, social media strategy, engagement, or audience growth, which can cause the skill to run in situations where the user did not explicitly ask for autonomous account actions. In the context of a skill that can post, schedule, and log activity, unintended invocation increases the risk of accidental account modification and persistence side effects.
- Content
Static analysis
No suspicious patterns detected.