sync-horizon
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell operations using
git,ls,cat, andheadto analyze the siblingeve-horizonrepository and executes a local validation script. These commands are necessary for its synchronization tasks. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: Data is read from
../eve-horizon(git logs, plan headers, and source code). Boundary markers: No explicit delimiters are used to separate ingested data from instructions. Capability inventory: The skill can execute shell commands and modify local files. Sanitization: Content from the external repository is processed without validation. - [SAFE]: The script
scripts/check-state-today.shcontains a hardcoded local path (/Users/adam/dev/incept5/eve-skillpacks). This is a minor best-practice violation and does not pose a functional security risk.
Audit Metadata