lovstudio-bp-polish
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Python script
scripts/audit_bp.pyto perform structural auditing of business plan outlines. This is a local execution of the skill's own code to provide deterministic linting. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of business plan outlines, PDFs, and PPTX files provided by the user.
- Ingestion points: The agent reads
outline.mdand user-provided documents (e.g.,project-bp.pdf) as described in the workflow. - Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for separating embedded content from agent instructions.
- Capability inventory: The skill can execute a local Python script (
audit_bp.py) and write output reports to thebusiness-plan/reports/directory. - Sanitization: No explicit sanitization or validation of the input business plan content is performed before the LLM processes it.
Audit Metadata