file-todos
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on a surface that ingests untrusted data from external sources, such as pull request comments and user feedback, to generate new task files.
- Ingestion points: The skill instructions specify creating todos from code findings, PR comments, and user feedback (SKILL.md).
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate untrusted external content within the generated markdown files.
- Capability inventory: The skill utilizes file system operations (cp, mv) and shell utilities (ls, grep, sort, tail, awk) to manage the lifecycle of task files.
- Sanitization: The instructions do not describe specific sanitization or filtering protocols for external content before it is persisted in the todo files.
Audit Metadata