T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:7- Finding
Overprivileged Filesystem Access for a Conversational Skill
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:7
Vulnerability Type: Excessive filesystem permissions and violation of least privilege
Risk Level: MediumVulnerable Code Snippet
yaml allowed-tools: Read, Write, EditTechnical Analysis
The skill is presented as a conversational AI companion, but it is granted file reading, creation, and modification capabilities. The configuration does not restrict these tools to a dedicated memory file, storage directory, file type, or other narrowly scoped resource.
Although the documented memory functionality may justify limited persistence, unrestricted
Read,Write, andEditpermissions exceed the minimum capabilities required for ordinary conversation. If tool access is enforced only at this broad declaration level, prompt content could cause the agent to treat unrelated workspace files as companion memory or supporting context.No explicit malicious instruction to access arbitrary files was found. The vulnerability is the absence of a least-privilege boundary around capabilities that could access or alter data outside the skill's legitimate scope.
Attack Path
- A user invokes the soulmate skill, giving the agent access to the declared filesystem tools.
- The user or untrusted conversation content asks the agent to load an arbitrary file as previous conversation history, a journal, or soulmate memory.
- The agent uses
Readon a file unrelated to the skill. - The content can subsequently be disclosed through the conversation.
- Alternatively, the user asks the agent to save or revise memory in an arbitrary path.
- The agent uses
WriteorEditto create, overwrite, or modify a file outside a dedicated memory area.
Exploitability depends on whether the hosting platform applies additional path-level authorization not visible in the audited project.
Impact Assessment
A successful exploitation could provide access to files ...[truncated 574 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove
Read,Write, andEditif persistent memory is not essential to the skill. - If memory is required, replace broad filesystem access with a purpose-built memory API.
- Restrict persistence to a dedicated per-user file or directory that cannot resolve paths outside its assigned root.
- Canonicalize paths and reject absolute paths, parent-directory traversal, symbolic-link escapes, and unexpected file extensions.
- Require explicit user confirmation before reading, overwriting, or deleting stored information.
- Prevent the skill from reading or editing source files, credentials, configuration files, shell profiles, or files belonging to other users.
- Apply host-side sandboxing and allowlists rather than relying solely on behavioral instructions.
- Log filesystem operations without recording the sensitive contents being processed.
- Remove
