Back to skill

Security audit

Writing Style And Tone

Security checks for vulnerabilities and agentic risk

Overview

This is a writing-editing skill whose broad writing triggers and publishing references are disclosed and bounded by human sign-off, with no tool code or hidden execution behavior found.

Installers should treat this as an editing and style-quality skill, not as permission to post content automatically. Before any scheduling or WoopSocial publication, require a separate explicit user approval of the final text, especially for public, crisis, sales, or brand-sensitive content.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description lists very broad situations such as when posts "sound like ChatGPT," a draft needs a style edit, or "any AI-assisted draft needs its mandatory quality pass." These triggers overlap with common writing requests and do not clearly define boundaries or exclusion conditions, increasing the chance of the skill being invoked too broadly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file instructs that after human sign-off, 'WoopSocial publishes,' which normalizes an external publishing action without an explicit user-warning or consent checkpoint in the skill text. In an agentic context, references to downstream publication can be interpreted as part of the expected workflow, increasing the risk that generated content is pushed to a third-party platform without sufficiently clear confirmation boundaries.

Content

No source excerpt is available for this finding.