project-learner
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
date,mkdir, andsedto create a directory structure and generate unique timestamps for log filenames. - [INDIRECT_PROMPT_INJECTION]: The skill is instructed to retrieve existing learning logs and follow any extra requirements or instructions found within them. This creates a surface for indirect prompt injection, as the agent may adopt behaviors specified in processed data.
Audit Metadata