yy-memory
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
git log,git diff) to gather information about recent changes in the project environment to inform memory updates.- [EXTERNAL_DOWNLOADS]: The script package defines several standard development dependencies (e.g., eslint, prettier, typescript) inscripts/package.jsonto be installed from the official NPM registry.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted repository data. - Ingestion points: git log and git diff outputs (untrusted commit messages/code).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands in the commit data.
- Capability inventory: Filesystem write access (creating/modifying .memory/ files), git command execution.
- Sanitization: No validation or filtering of git output is performed before processing.
Audit Metadata