T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:16- Finding
Excessive Command Execution Privileges and Unsafe Elevation Guidance
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This file-organizer skill is not clearly malicious, but it requests broad write and command-execution authority for file cleanup tasks without enough safeguards.
Install only if you are comfortable granting an agent broad local file modification and command-execution capability. Use it only on backed-up, non-sensitive folders, insist on a preview plan before any move/delete action, avoid administrator/root execution, and do not provide API keys unless the skill clearly explains what data will be sent externally.
SKILL.md:16Excessive Command Execution Privileges and Unsafe Elevation Guidance
The skill advertises file classification and duplicate cleanup but does not prominently warn that these operations can move, rename, or remove user data. In a file-management context, lack of a destructive-operation warning is especially dangerous because users may assume a safe preview while the skill could perform irreversible changes.
A file organizer generally needs filesystem read/write operations, but unrestricted or loosely described system command execution greatly expands the attack surface. If an agent follows these instructions, ambiguous user input could be transformed into shell actions that modify the system, delete data, or run arbitrary programs beyond the stated purpose of organizing files.
The invocation guidance is broad enough to match many unrelated requests, increasing the likelihood that the skill activates outside its intended context. In a skill with write and exec capabilities, over-broad triggering is dangerous because it can cause the agent to apply high-impact operations to requests that did not clearly ask for file reorganization.
The skill claims to organize local files, yet it introduces external API usage and API key handling without a clear necessity. This creates unnecessary data-exposure risk because file names, paths, contents, or metadata could be transmitted off-host, and it also encourages handling secrets in a workflow that should not need them.
The example trigger phrases are extremely short and do not communicate what actions may be taken, whether files will be moved, renamed, or deleted, or whether duplicate cleanup is enabled. In context, this makes accidental destructive execution more likely because users may invoke the skill casually without understanding the consequences.
The skill is presented as a local file organizer, but the documentation later broadens its scope to API integration and command execution. This mismatch is dangerous because users or agents may grant the skill permissions appropriate for harmless file sorting while it is actually positioned to invoke external services and execute system-level actions, increasing the chance of over-privileged or unintended behavior.