todo
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a project's
TODO.mdfile and executes the tasks described within it, creating a surface for indirect prompt injection. - Ingestion points: The skill reads
TODO.mdfrom the project root to find tasks to execute. - Boundary markers: There are no boundary markers or instructions to treat the content of
TODO.mdas untrusted data or to ignore embedded instructions. - Capability inventory: The skill is granted broad capabilities, including finding relevant files, implementing solutions (file writes), and verifying work by running tests (command execution).
- Sanitization: No sanitization, validation, or filtering is performed on the tasks read from the
TODO.mdfile before they are interpreted and executed by the agent.
Audit Metadata