T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:11- Finding
Unnecessary Shell and Local File Access Permissions
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:11
Vulnerability Type: Excessive tool permissions violating least privilege
Risk Level: MediumVulnerable Code:
yaml allowed-tools: Bash, ReadTechnical Analysis
The skill grants access to
BashandRead, but its documented workflow only requires generating and refining a fractional CFO client education handout. The declared APIs arechatandimage_generation, and no documented workflow step requires shell command execution or arbitrary access to local files.These permissions unnecessarily expand the skill's security boundary.
Bashcan provide broad command-execution capabilities under the agent process's operating-system identity, whileReadmay expose any local files accessible to that identity. Although the reviewed skill contains no direct malicious command or file-read instruction, excessive authorization increases the consequences of future instruction injection, compromised referenced content, or unsafe modifications to the skill.Attack Path
- A user installs and loads the skill with
BashandReadenabled. - The skill or content processed during a handout-generation session is later modified or contains attacker-controlled instructions.
- Those instructions induce the agent to invoke the unnecessarily authorized tools.
- The agent reads accessible local files or executes shell commands outside the legitimate handout-generation workflow.
- Retrieved information may be exposed through generated output, while shell commands may alter files or execute other processes within the agent account's permissions.
The current repository does not contain the malicious instructions required to complete this path; the finding concerns the avoidable privilege exposed if such instructions are introduced.
Impact Assessment
Successful exploitation could provide access to files readable by the agent's operating-system acco ...[truncated 468 chars]
- A user installs and loads the skill with
- Remediation
View remediation
Remediation Suggestions
- Remove
BashandReadfromallowed-toolsbecause neither is required by the documented workflow. - Authorize only the capabilities necessary for content generation, such as the declared
chatandimage_generationAPIs. - If file access is later required, replace arbitrary reads with narrowly scoped access limited to explicit user-selected input and output locations.
- If command execution becomes necessary, expose specific fixed operations rather than a general-purpose shell, validate all arguments, and run them in a sandbox with minimal filesystem and network access.
- Add a permission review to release checks so newly requested tools must be justified by a documented workflow step.
- Remove
