planning-horizons
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a framework for receding-horizon planning based on established academic sources. It utilizes local Node.js scripts for deterministic arithmetic calculations without requiring network access or elevated privileges.
- [COMMAND_EXECUTION]: The skill utilizes the node command to run a calculation script (scripts/calc.js) included in the skill package. This is a standard functional requirement for the skill's described purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied planning data, creating a potential ingestion surface. 1. Ingestion points: depths.json and backlog.json (SKILL.md). 2. Boundary markers: None explicitly defined. 3. Capability inventory: Subprocess execution via node (SKILL.md). 4. Sanitization: None observed in markdown instructions. The risk is assessed as safe because the processed data is used for deterministic mathematical triage.
Audit Metadata