recall
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on local project context retrieval and indexing. It does not exhibit any malicious patterns such as data exfiltration or unauthorized access.
- [COMMAND_EXECUTION]: The skill instructions prompt the agent to execute local Python scripts (
recall_context.pyanddecision_replay.py) included in the skill's package. These scripts are used to aggregate and process project metadata and weekly history files. - [DATA_EXFILTRATION]: No network communication or exfiltration patterns were detected. All file operations are restricted to the local project directory and a user-defined knowledge vault.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project history data stored in JSON format. While this data is technically external to the skill's code, it is retrieved from the user's own local vault. The risk of indirect injection is minimal and considered a standard aspect of data retrieval functionality.
Audit Metadata