T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:285- Finding
Default Read-Only Tier Exposes State-Changing Tools and Excessive Sensitive-Data Access
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 21, 102, 274, 285–287, 362, and 369
Vulnerability Type: Least-privilege violation and inconsistent authorization boundary
Risk Level: MediumThe skill describes the default
MESSAGEStier as read-only, but its documented heartbeat tool set includes capabilities that can create todos, create notes, and modify durable memory. The documentation does not state that these tools are restricted to theACTIONStier.Vulnerable Code Snippets
SKILL.md, line 21:markdown | Tier | `MESSAGES` (default) = read-only checks + summary. `ACTIONS` = can take write actions (future). |SKILL.md, line 102:markdown - `MESSAGES` — read-only checks, delivers summary message (default)SKILL.md, line 274:markdown 3. **Memory context**: loads user's long-term memory for personalizationSKILL.md, lines 285–287:markdown - `search_todos` / `create_todo` — task management - `search_notes` / `create_note` — workspace notes - `memory_write` — save durable facts (rate-limited: 1 write per 60min, max 4 daily entries)SKILL.md, line 362:markdown - **context-sync**: Heartbeat's `memory_write` tool keeps long-term memory updatedSKILL.md, line 369:markdown - Heartbeat excluded tools prevent unintended write actions in MESSAGES tierTechnical Analysis
A read-only authorization tier should expose only operations that cannot modify user or system state. However, the documented tool set includes
create_todo,create_note, andmemory_write, all of which perform persistent writes.The claim that only “write-heavy” tools are excluded does not establish a reliable authorization boundary. No documented server-side or tool-dispatch restriction ensures that these three write operations are unavailable under
MESSAGES. Rate limitingmemory_writereduces frequency but does not make th ...[truncated 2132 chars]- Remediation
View remediation
Remediation Suggestions
- Implement a server-side, deny-by-default tool allowlist for each policy tier. Under
MESSAGES, expose only explicitly approved search and read operations. - Remove
create_todo,create_note, andmemory_writefrom theMESSAGEStool registry. Do not rely solely on prompt instructions to prevent their use. - Permit persistent writes only under
ACTIONS, after explicit user opt-in. For sensitive or externally visible changes, require per-action confirmation. - Validate the active tier again at the tool-execution boundary so that a model-generated call cannot bypass policy checks.
- Treat email, notes, memory, and other retrieved content as untrusted data. Clearly separate retrieved content from system instructions and reject embedded requests to invoke tools or alter policy.
- Apply minimum necessary data scopes, such as limited time windows, result counts, and selected mailboxes or folders.
- Record the tier, requested tool, authorization decision, sanitized arguments, and result for every tool call. Surface denied write attempts in run details.
- Provide a review and rollback mechanism for todos, notes, and memory entries created by autonomous runs.
- Add automated authorization tests proving that every state-changing tool is rejected while the active tier is
MESSAGES. - Update
SKILL.mdso its tier descriptions and security claims exactly match the enforced implementation.
- Implement a server-side, deny-by-default tool allowlist for each policy tier. Under
