gsd-plant-seed
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates by executing a local workflow file located at
/home/delorenj/code/bhappy/.codex/get-shit-done/workflows/plant-seed.md. This architecture relies on local resources provided by the author and does not perform any remote code execution or network-based downloads. - [SAFE]: Actions performed by the skill, such as writing to the
.planning/seeds/directory and requesting user input, are standard functional behaviors for a project management tool and are confined to the local project environment. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it captures user-supplied text to be stored and later processed by other tools. This is a low-risk surface given the local nature of the skill and its primary purpose.
- Ingestion points: User input captured via the
{{GSD_ARGS}}parameter inSKILL.md. - Boundary markers: Not explicitly defined in this skill wrapper.
- Capability inventory: Spawns sub-agents (
spawn_agent) and writes to local project files (.planning/seeds/). - Sanitization: The skill wrapper does not perform explicit sanitization of the user-provided content before storage.
Audit Metadata