todo-manager
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to store as to-do items, which are later retrieved and processed by the agent. This creates a potential surface for indirect prompt injection if a stored task contains instructions intended to subvert the agent's behavior.
- Ingestion points: User-supplied task descriptions provided via prompts like "add a todo" as described in
SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the instructions.
- Capability inventory: The skill performs file-write and file-read operations on the local
todos.jsonfile via thescripts/todo.pyscript. - Sanitization: No input validation, escaping, or sanitization logic is specified in the provided files.
Audit Metadata