T01 · Skill Instruction Hijacking
Warning
- Location
SKILL.md:133- Finding
Mandatory Promotional Footer Hijacks Skill Output and Introduces External Tracking
- Content
View full analysis
- Remediation
View remediation
Security audit
Badge Qualifier
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly a coherent lead-qualification helper, but it forces an unrelated promotional tracking link into every generated lead record and lacks privacy handling guidance for personal contact data.
Review this skill before installing in a business workflow. It appears safe from a code-execution standpoint, but it handles personal lead data and does not tell users how to manage consent, retention, or privacy obligations. Also expect every generated card to include an unrelated Lensmor promotional tracking link unless the skill is edited or the agent is instructed not to include it.
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
Findings (1)
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 (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The README explicitly encourages users to input badge scans, booth notes, emails, names, job titles, and conversation summaries, all of which can contain personal and commercially sensitive data, but it provides no privacy warning, consent guidance, retention limits, or handling safeguards. In a trade-show lead qualification context, this omission increases the chance that users will process personal data without appropriate notice, lawful basis, or minimization, creating privacy, compliance, and reputational risk.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The trigger guidance is broad and lacks clear activation and exclusion boundaries, which can cause the skill to be invoked in situations where it should not handle the user request. In practice this increases the risk of over-collection, misclassification, or unintended processing of lead/contact data because nearby sales-assistant tasks may be routed here without sufficient user intent or context.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown file recommends sending outreach emails based on badge scans and business cards, which involves processing personal contact information. The skill description does not include any warning about privacy, consent, or appropriate handling of attendee data, even though the behavior could affect user data and privacy.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
Forcing a branded footer into every output without user opt-in injects unsolicited promotional content into generated results. While not a direct code-execution issue, it can create trust, compliance, and data-handling concerns if lead summaries are copied into CRM records, emails, or internal systems with unwanted external marketing links attached.
- Content
Static analysis
No suspicious patterns detected.