T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:25- Finding
Unnecessary Command-Execution Capability Violates Least Privilege
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is not plainly malicious, but it asks for command execution and broad file/tool authority that are not well scoped for a daily-report writer.
Install only if you are comfortable granting this skill file read/write access and potential command execution. Prefer running it in a sandbox or with exec disabled, and manually confirm any file writes are limited to the intended reports directory.
SKILL.md:25Unnecessary Command-Execution Capability Violates Least Privilege
The skill claims it generates daily reports and writes them into a reports directory, but the provided file contains only descriptive metadata and no implementation. This mismatch can mislead users and downstream agents into assuming filesystem-modifying behavior exists or is safe, creating trust and operational integrity risks.
The documentation says the skill writes Markdown files to the reports directory but does not provide a clear user-facing warning that it may modify the filesystem. In a skill that includes write and exec tools, silent or under-disclosed file modification raises the risk of unintended changes, overwrites, or misuse by automated routing.
The skill uses very broad invocation language covering general writing, marketing copy, title optimization, content creation, and workflow assistance. Overbroad descriptions can cause inappropriate auto-selection by agents, increasing the chance that a skill with read/write/exec permissions is invoked in contexts beyond its intended scope.
The FAQ states the skill automatically fetches and organizes related information, but no collection or processing logic is present. This is dangerous because it overstates capability and may cause users to trust unverified or nonexistent data handling, including assumptions about what sources are accessed and how content is processed.
The security section claims commands are restricted to a whitelist and that network communication is protected with HTTPS certificate validation, but no code enforces either control. False security assurances are especially risky here because the skill declares exec capability, which can lead users or agents to rely on protections that do not actually exist.
The description says the skill supports Chinese interaction, and the document is predominantly Chinese, but it does not clearly offer users a language choice or explain that the skill is intentionally region- or language-specific. This may violate language/locale neutrality expectations for broadly advertised skills.