perfectcode-zen-plan
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git statusandgit logto gather codebase context. This is a standard and safe operation for a development-focused planning tool. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user requirements and external codebase content during the planning phase.
- Ingestion points: User feature requests and codebase context gathered via
gitand the@exploreagent. - Boundary markers: The workflow does not explicitly define delimiters or instructions to ignore embedded malicious commands within the analyzed content.
- Capability inventory: The skill performs file writes to the
.opencode/plans/directory and executes shell commands for git context. - Sanitization: There is no evidence of sanitization or filtering for the data ingested from the user or the codebase before it is synthesized into the final plan.
Audit Metadata