T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:11- Finding
Unnecessary Shell Execution and File-Read Permissions
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, line 11
Vulnerability Type: Excessive tool permissions violating least privilege
Risk Level: MediumVulnerable Code
yaml description: "Create a polished explainer handout with visuals, FAQs, and clear next steps for a home remodeling company. Use when handling client education work for..." > 📖 **Complete setup guide**: https://skillboss.co/skill.md allowed-tools: Bash, ReadTechnical Analysis
The skill is intended to generate a client education handout, and its declared APIs are
chatandimage_generation. This content-generation purpose does not inherently require arbitrary shell command execution or access to local files.Declaring
BashandReadtherefore expands the skill's authority beyond its documented functional requirements. If the host platform enforcesallowed-toolsas an authorization boundary, the skill may be able to execute operating-system commands and inspect files accessible to the agent process. This increases the consequences of prompt injection, malicious user input, or unsafe content incorporated into the generation workflow.No instruction in the reviewed files directly attempts to exploit these permissions. The vulnerability is the unnecessary exposure of privileged tools, rather than evidence of active command execution or data theft.
Attack Path
- A user or an untrusted content source supplies crafted instructions while the skill is active.
- The injected instructions induce the agent to invoke
ReadorBash, despite those tools not being required for handout generation. Readis used to inspect files available to the agent process, orBashis used to execute local commands.- Data obtained through those tools could be incorporated into generated output or otherwise exposed. Shell commands could also modify files or invoke other locally available programs, subject to the host process's operating-system permissions and sandbo ...[truncated 840 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove
BashandReadfromallowed-tools. - Grant only the content-generation capabilities required by the documented workflow, such as
chatandimage_generation. - If file input becomes necessary, replace unrestricted file access with a narrowly scoped mechanism limited to explicit user-selected files and approved directories.
- If command execution later becomes essential, expose a purpose-built tool with fixed arguments instead of a general shell. Require explicit user confirmation and execute it in a restricted sandbox.
- Add runtime controls that deny access to secrets, home directories, credentials, and unrelated project files.
- Validate tool use against the skill's documented purpose and reject tool requests originating from untrusted handout content or embedded instructions.
A minimized configuration should resemble:
yaml allowed-tools: []Alternatively, list only the exact generation tools required by the host platform, without enabling general shell or filesystem access.
- Remove
