Shadow Command Trigger
Medium
- Category
- Trigger Abuse
- Confidence
- 70% confidence
- Finding
Shadow Command Trigger: 'write about' conflicts with built-in command 'write'
- Content
Security audit
botlearn-writer
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed article-writing skill with broad but low-impact writing triggers and no evidence of hidden execution, persistence, or data exfiltration.
Before installing, be aware that this skill may activate on broad writing prompts, not only explicit article requests. It appears safe for writing assistance, but users who prefer precise activation should narrow the triggers or invoke it only for article/blog drafting.
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
- 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 (4)
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
md - **Symptoms**: The same citation appears in every argument block; all expert quotes come from one person - **Fix**: Use a minimum of 3-5 independent sources per article. Cross-reference key claims across multiple sources. Diversify evidence types (statistics, expert opinion, case studies) ### 10. Appeal to Authority Without Verification - **Problem**: Citing an "expert" without verifying their credentials or relevance to the specific topic - **Symptoms**: "A Harvard professor says..." without specifying their field; quoting a tech CEO on medical topics - **Fix**: Verify that the expert's credentials are relevant to the specific claim being made. Include their specific role, institution, and relevant qualification
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The trigger phrases are broad and include generic terms like "compose" and "write about," which can match many ordinary user requests and cause the skill to activate unintentionally. Over-broad activation increases the chance of inappropriate tool use and unexpected delegation to this skill when a narrower or safer behavior was intended.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The activation rule "WHEN the user requests article writing, composition, or blog post creation" is ambiguous because "composition" can refer to many unrelated writing tasks. This can cause the skill to activate for general writing assistance, broadening access to its linked tools and workflows beyond the intended scope.
- Content
Static analysis
No suspicious patterns detected.