td-task-management
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by storing and retrieving human-readable text (task descriptions, logs, and decisions), which creates a standard surface for indirect prompt injection if external or untrusted data is recorded.
- Ingestion points: Data enters the system via
td create,td update,td log, andtd handoffcommands as documented inSKILL.mdandreferences/quick_reference.md. - Boundary markers: The instructions do not define specific delimiters for separating user-provided data from agent instructions.
- Capability inventory: The agent is instructed to read this stored data using
td usageandtd contextto determine its next actions and restore project context. - Sanitization: The documentation does not specify sanitization or validation requirements for the text inputs recorded by the tool.
- [SAFE]: The skill primarily consists of documentation and workflow guidance. It does not include executable code, external dependency installations, or network operations outside of the described CLI tool's local SQLite storage functionality.
Audit Metadata