plan-based-skill-builder

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill functions as a meta-tool for documentation and skill creation, assisting in the extraction of workflows from planning documents.
  • [COMMAND_EXECUTION]: Includes example system commands such as kill, make, and curl within templates for system restarts and deployments. These commands are contextually appropriate for the described operations.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted external plan documents. 1. Ingestion points: Reads from plan documents (e.g., *PLAN*.md). 2. Boundary markers: The skill does not explicitly define markers to isolate or ignore instructions embedded within the source documents. 3. Capability inventory: The skill facilitates the creation of new skills that may execute bash commands and system-level operations. 4. Sanitization: No specific sanitization or validation of the input plan content is performed during the extraction process.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 02:19 PM