todos
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from a user-controllable file, creating a surface for indirect prompt injection.
- Ingestion points: Reads content from
/workspace/personal/todos.md(SKILL.md). - Boundary markers: No specific delimiters or safety instructions are defined to separate the todo data from the agent's instructions.
- Capability inventory: The skill involves reading and writing to the local workspace filesystem.
- Sanitization: No sanitization or validation of the file content is described before the agent processes or summarizes the tasks.
Audit Metadata