gtm-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize search tools such as
globandgrepto analyze the local project directory. This behavior is used to identify React/Vue components, tracking markers, and analytics configuration, which is the primary purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content by scanning the local codebase and reading project-generated files to determine business models and tracking requirements.
- Ingestion points: Reads local source code files (
.tsx,.jsx,.vue), project configuration (package.json), and external analysis files (audit-report.json,gtm-context.md). - Boundary markers: No explicit delimiters or instructions are used to separate ingested data from agent instructions.
- Capability inventory: The skill reads local files, executes filesystem search commands, and writes a tracking plan JSON file to the project root.
- Sanitization: No sanitization or validation of the ingested codebase content is specified.
Audit Metadata