todo-create
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by instructing the agent to read and process markdown files from the
.context/systematic/todos/andtodos/directories. These files could potentially contain malicious instructions intended to influence the agent's behavior. - Ingestion points: Markdown files in
.context/systematic/todos/andtodos/(referenced in SKILL.md). - Boundary markers: None; the instructions do not specify delimiters or warnings to ignore embedded agent commands within the todo files.
- Capability inventory: The skill uses file system tools to create, move, and rename files (
mkdir -p,mv) and leverages file-search/glob tools for reading content. - Sanitization: No sanitization or validation logic is described for the content of the markdown files being read.
Audit Metadata