tree-ring-memory
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to download an installation script from
https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/v0.15.0/install.sh. It implements significant mitigations by requiring the agent to verify the SHA-256 hash of the script (ef0d5eb8f09cbe2e4c3abe80ee9a98a56759c89ad4ddd103d6c68314cd653ade), instruct the user to inspect the file, and obtain explicit authorization before execution. - [COMMAND_EXECUTION]: The skill relies on several shell commands for its core functionality, including the
tree-ringCLI for memory management,sedfor extracting guidance from project files, andshfor running the installer. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and acts upon data found in project-local files, which could contain instructions intended to influence the agent.
- Ingestion points: The skill reads configuration data from
.tree-ring/SKILL.mdand.tree-ring/CLI.mdusingsed, and retrieves stored memory entries viatree-ring recall. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within these project-local files.
- Capability inventory: The agent is authorized to execute shell commands, perform file system operations (read/write for memory), and make network requests for tool updates.
- Sanitization: The instructions do not define any sanitization or validation logic for the content retrieved from project files or memory storage.
Audit Metadata