Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:
Security audit
Linkedin Thread Monitor
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed LinkedIn comment-monitoring and draft-assistance workflow with no executable code, persistence, or automatic posting behavior.
Install only if you are comfortable using an Apify token to retrieve recent LinkedIn thread data and having the agent draft replies or DMs. Review every suggested reply, DM, and growth tactic manually, and avoid coordinated engagement or outreach that would violate LinkedIn rules or your own outreach standards.
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
Vulnerability Patterns
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The reference content expands the skill from monitoring and triaging LinkedIn comment threads into prescriptive growth tactics, DM outreach, and coordinated engagement guidance. In an agentic setting, this can cause the system to generate or encourage manipulative social-platform behavior outside the declared scope, increasing the risk of spammy outreach, platform-policy violations, and unwanted automated engagement actions.
- Content
Static analysis
No suspicious patterns detected.