T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:10- Finding
Broad Automatic Access to Persistent Local Agent Knowledge
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 10–14 and 27–29
Vulnerability Type:T05: Unauthorized Access and Privilege Escalation
Risk Level: MediumComplete Relevant Snippet
The following is an English translation of the relevant Skill instructions:
markdown - Automatic trigger: When receiving a task with a clear objective and target, before beginning substantive processing, extract short phrases based on the task object or domain, objective or action, and key issue, and lightly search the experience/current INDEX for relevant experience. - Automatic trigger: Existing project locations, file summaries, historical decisions, stable rules, failure guardrails, or similar experience may materially affect the current judgment or action. - Automatic trigger: Before using an external tool to send, publish, modify, delete, deploy, authorize, or approve something, or when an external tool returns an abnormal result and a retry is being prepared, extract short phrases based on the tool or product, action, and key object, and search the experience index. - Automatic trigger: The message or context contains a project, path, or file name, or retrospective clues such as “previously,” “before,” “similar,” “rules,” “history,” or “why it was done this way.” - Automatic trigger: The current conclusion may conflict with an old conclusion, existing responsibility, or existing practice, requiring a search before judgment.markdown - The data root consists of Markdown files, CSV files, original file paths, and current system state under `~/.agent-knowledge/`; the INDEX.md file in each of the four knowledge and experience directories is read first, while `archive/` is not read by default. - Use the host's native read-only file API, fixed-string search, and safe Markdown/CSV parsers; do not depend on a particular command, runtime, or network connection. - For long files, read only the relevant headings, para ...[truncated 3160 chars]- Remediation
View remediation
Remediation Suggestions
- Require explicit user approval before accessing
~/.agent-knowledge/, except when the user directly requests a historical or knowledge-base lookup. - Remove the automatic trigger for every task with a clear objective and target. Trigger retrieval only when persistent knowledge is necessary to fulfill the request.
- Limit searches to the current project, workspace, customer, or tenant scope. Reject entries whose scope cannot be conclusively matched.
- Present candidate source names and scopes before opening their full contents, particularly when they reference files outside the current workspace.
- Introduce a default-deny policy for credentials, personal data, private keys, environment files, security incident records, and other sensitive paths.
- Prevent persistent information from being reproduced in responses unless it is directly relevant and the user is authorized to receive it.
- Keep the existing read-only restrictions and enforce them at the tool-permission layer rather than relying solely on natural-language instructions.
- Record provenance internally for retrieved facts so that current workspace evidence can take precedence over historical material without exposing unrelated source content.
- Apply strict per-task retrieval limits and clear retrieved context when the task or project scope changes.
- Require explicit user approval before accessing
