T08 · Insecure Dependencies
Warning
- Location
RELEASE.md:10- Finding
Unverifiable Installation of an Unpinned Dependency from an Unspecified Source
- Content
View full analysis
- Remediation
View remediation
Security audit
Gonggong Hwpxskills Main
Security checks for vulnerabilities and agentic risk
Overview
The skill appears to be a local HWPX document-template helper, but its installation guidance points users toward missing files and an unspecified source dependency that could be unsafe to install.
Review this before installing. The document-processing purpose is reasonable, but do not install python-hwpx from an arbitrary source or follow missing install.sh/requirements.txt instructions unless the publisher provides a canonical repository, pinned version or commit, and verification details. Treat the current package as incomplete until the missing runtime files and dependency instructions are fixed.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
- 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 (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The README text is written as a Korean-only description and presents the skill purpose in a way that implies operation in Korean without offering any language or locale choice. Under the policy rule, forcing a specific language without user opt-in or documented regional justification is a natural-language policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The README description is written only in Korean and presents the skill as a document-writing capability without indicating that language use is optional or region-specific. Under the policy rule, a skill that effectively imposes a specific language without opt-in can be a locale-policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
The file includes natural-language content from an unresolved merge conflict, mixing competing descriptions and languages without clarifying which user-facing text should apply. This can create a de facto language/locale experience that is not explicitly chosen by the user and is not documented as region-specific.
- Content
Static analysis
No suspicious patterns detected.