Back to skill

Security audit

interactive-content

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed social-content planning skill with human-controlled posting limits and privacy guardrails.

Before installing, confirm you are comfortable with a skill that drafts interactive social campaigns and feed-post content for publishing workflows. Native stickers, live AMAs, personal answers, contests, and sensitive-topic polls should remain human-reviewed and consent-based, as the artifact instructs.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/mechanics-and-templates.md (reported line 44)May include surrounding context.

md
## Never
Run filler polls with no job · leave a loop unclosed · post a bare "AMA" · rig or fabricate results · astroturf
questions from fake accounts · punish wrong quiz answers · fabricate quiz facts · harvest sensitive data via
casual polls (answers aren't anonymous) · expose an individual's answer without consent · claim WoopSocial
attaches stickers or auto-DMs · dress a Story poll up as research.