decide
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill manages a local decision log by creating directories and writing or moving files within the user's home directory (e.g.,
~/.config/makerskills/decide/archive/). These operations are used to maintain a persistent history of decisions. - [PROMPT_INJECTION]: The skill ingests user responses which are then stored in markdown files, creating a surface for indirect prompt injection.
- Ingestion points: User-provided context and answers to the decision questions (SKILL.md Step 1 and Step 3).
- Boundary markers: Not present; user data is interpolated directly into markdown templates without specific delimiters or isolation instructions.
- Capability inventory: The skill possesses file-write and file-move capabilities used to manage the archive directory.
- Sanitization: User input is processed verbatim and not subjected to escaping or validation before being written to disk.
Audit Metadata