T09 · Insecure Skill Coding Practices
Warning
- Location
prompts/prompt1.md:75- Finding
Mandatory generation of unverified environmental compliance claims
- Content
View full analysis
- Remediation
View remediation
Security audit
Auto Detailing Car Wash Kit
Security checks for vulnerabilities and agentic risk
Overview
This skill is a marketing-content generator with no code execution, but it can produce unsupported legal/commercial claims that users may publish as advertising.
Review and substantiate every regulatory, certification, rating, price, and performance claim before publishing. Do not use the mobile-water or fleet-savings copy unless the business has documented evidence for the exact claim, and treat generated outreach as draft marketing copy requiring human compliance review.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
prompts/prompt4.md:153- Finding
Cold outreach prompt permits fabricated customer performance metrics
- Content
View full analysis
- Remediation
View remediation
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 (2)
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
-
Mobile water: For CA, NV, AZ: include "All mobile services use EPA-compliant water containment. Wash water is collected and disposed per [state] stormwater regulations — we never discharge to storm drains."
-
IDA / certification claims: "IDA Certified Detailer" only if current IDA certification confirmed in inputs. "Gtechniq Authorized Detailer" only if current authorization confirmed. Do not use certification language without confirmation.
Output all selected service pages sequentially, each with complete JSON-LD.
text -
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The prompt requires generation of SMS, email, social, and review-response templates entirely in English and provides no option for the user to choose another language or locale. Because the skill produces end-user communications, this is a natural-language policy concern when no opt-in or documented locale constraint is present.
- Content