T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:11- Finding
Insufficiently Scoped Access to Repository and Agent Memory
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:11, 26-27
Vulnerability Type:T05: Unauthorized Access and Privilege Escalation
Risk Level: SuspiciousVulnerable Code
markdown 1. Gather repo memory files and current auto-memory context.markdown ## Inputs - Repo memory files - Auto-memory stateTechnical Analysis
The skill directs the agent to gather repository memory files and the current auto-memory state without defining path boundaries, permitted file types, exclusions, redaction requirements, or data-minimization controls. These memory layers may contain private preferences, prior-session information, sensitive operational instructions, or secrets accidentally recorded by users.
Access to memory is related to the skill's stated purpose, so the reviewed text does not demonstrate deliberate privilege escalation or malicious exfiltration. However, the unrestricted collection instruction may cause the agent to access and place more sensitive information into its active context or report than is necessary for a particular review.
The skill includes mitigating controls at
SKILL.md:14-15by requiring a grouped report and explicit approval before changes. Those controls restrict writes but do not adequately constrain the initial read and collection operation.Attack Path
- A user invokes the memory landscape review skill.
- The agent interprets “repo memory files” and “current auto-memory context” broadly.
- The agent reads repository, local, personal, or auto-memory entries without first presenting an explicit access scope.
- Sensitive entries are loaded into the active model context.
- Those entries may be reproduced or summarized in the grouped report, exposing information beyond the user's intended review scope.
No instruction to transmit the collected information over a network, execute code, establish persistence, or alter memory without approval was foun ...[truncated 595 chars]
- Remediation
View remediation
Remediation Suggestions
- Require the agent to enumerate candidate memory file paths before reading their contents.
- Obtain explicit user approval for the proposed read scope, especially for personal, local, and auto-memory.
- Define an allowlist of supported memory files and directories instead of using open-ended collection language.
- Exclude credentials, environment files, authentication tokens, private keys, and unrelated conversation records.
- Apply secret detection and redaction before memory content is included in model context or reports.
- Read only the minimum content required to classify each memory entry.
- Separate approval for repository-shared memory from approval for personal or auto-memory.
- Report sensitive entries by location and classification rather than reproducing their complete values.
- Retain the existing requirement that no promotions, cleanup, or other writes occur without explicit approval.
