T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:166- Finding
Obsolete MD5-Based Custom Request-Signing Scheme
- Content
View full analysis
- Remediation
View remediation
Security audit
China API Doc Generator
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-writing skill with no executable code or persistence, but its sample signature-auth guidance includes weak MD5-based advice users should not copy into real systems.
Installers should treat this as a writing aid, not a security design authority. It is reasonable for Chinese API documentation workflows, but review or replace the MD5/app_secret signing template before using generated docs for production authentication, and preserve any user-requested language or timezone that differs from the skill defaults.
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
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly instructs the agent to generate documentation in a specific language/locale and style for Chinese developers without indicating that this should be conditioned on user preference. In practice, this can override a user's requested language or audience, causing unintended disclosure, usability issues, or policy misalignment when the user expects another locale.
- Content