teamai-share-learnings
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
teamai contributecommand to upload generated documentation to a remote repository as part of the intended workflow. - [INDIRECT_PROMPT_INJECTION]: The skill summarizes session history, which inherently creates a surface for indirect prompt injection from untrusted session content.
- Ingestion points: Reads the full history of the current AI session.
- Boundary markers: None; the prompt does not include delimiters to separate session data from instructions.
- Capability inventory: Can write local files and execute the
teamaiCLI tool. - Sanitization: No content sanitization is mentioned before data is processed and uploaded.
Audit Metadata