T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:59- Finding
Generation of Unverified Warranty, Safety Certification, and Customer Support Claims
- Content
View full analysis
- Remediation
View remediation
Security audit
CN to EN Listing Writer
Security checks for vulnerabilities and agentic risk
Overview
This is a text-only Amazon listing-writing skill with no code execution, persistence, credential use, or hidden data access, but users should verify any generated warranty or safety claims.
Install only if you want help drafting Amazon listing copy. Treat the output as marketing draft text, not verified compliance advice: confirm warranties, certifications, safety claims, support terms, measurements, and Amazon policy fit before publishing.
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 (1)
Vulnerability Patterns
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger list contains broad phrases such as 'listing translation' and 'cross-border seller' that can activate the skill in contexts far beyond its intended purpose. Over-broad invocation increases the chance of accidental routing, causing unrelated user content to be processed under this skill and potentially overriding a more appropriate or safer skill path.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill is described as converting input into English listings and emphasizes writing for Western buyers, but it does not offer a language choice or explicit opt-in for output locale. This can violate language/locale policy guidance when a skill forces a specific language behavior by default.
- Content