T03 · Remote Payload Retrieval and Execution
- Location
SKILL.md:39- Finding
Unpinned Remote Repository and Dependency Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill matches a fraud-detection purpose, but it asks users to run unverified remote code and gives little control guidance for sensitive financial and identity data.
Review this before installing. Only run it in a restricted virtual environment or container, pin the repository to a reviewed commit, verify dependencies, and avoid providing real identity documents, account records, or transaction histories until the publisher documents data handling and provenance.
SKILL.md:39Unpinned Remote Repository and Dependency Execution
The skill description is broad and does not define clear activation triggers, scope limits, or invocation constraints for high-sensitivity functions like transaction monitoring and identity verification. In an agent ecosystem, this can cause the skill to be invoked in unintended contexts, increasing the chance of over-collection, over-processing, or misuse of sensitive financial and identity data.
The markdown omits warnings that the skill handles highly sensitive activities: identity verification and transaction monitoring. Without prominent disclosure and consent language, users may provide personal, financial, or account data without understanding the privacy, compliance, and surveillance implications, which is especially risky in fraud and KYC-style contexts.
All user-facing natural-language content in the skill metadata and documentation is presented only in Chinese, with no indication of language choice or opt-in. This may violate organizational language/locale policy where user-facing skills are expected to offer language selection or clearly document locale restrictions.
The manifest description is written only in Chinese ("AI 反欺诈检测 - 交易风控、身份验证"), which may indicate a language-specific constraint without any stated user choice or opt-in. Under the policy rule for language or locale violations, this can be a concern when the skill appears to impose a specific language implicitly.