speak-memory
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a Python script (
scripts/manage-stories.py) to handle administrative tasks like archiving completed stories and rebuilding indexes. The script includes protections against path traversal and only operates within the designated.speak-memory/directory. - [EXTERNAL_DOWNLOADS]: No external downloads or remote dependencies are used. The skill operates entirely on local project files.
- [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were found. The skill reads and writes story data exclusively to the local filesystem.
- [PROMPT_INJECTION]: The instructions are focused on task tracking and do not contain patterns typical of prompt injection or safety bypass attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated story objectives and checklists. While these represent an ingestion surface, the risk is mitigated as the data is used for local tracking and the script provides sanitization for markdown table characters.
Audit Metadata