business-plan-generator

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow involves generating a Python script based on user input and executing it to create a PowerPoint file. This is the intended functional behavior for generating structured documents.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it interpolates user-provided text into a Python script that is subsequently executed.
  • Ingestion points: Business plan information provided by the user in response to the Step 1 questionnaire (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Execution of locally generated Python scripts via the environment's interpreter.
  • Sanitization: Not specified in the instructions; the agent is responsible for safely handling user strings during code generation.
  • [EXTERNAL_DOWNLOADS]: The skill relies on the python-pptx library, which is a standard community package for programmatically creating PowerPoint files.
  • [SAFE]: Analysis of the instructions and the provided script template revealed no malicious intent, data exfiltration patterns, credential harvesting, or unauthorized network operations. The author references a related tool for HTML conversion (wulaosiji/skills/BP_to_HTML), which is a vendor-owned resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:11 AM
Security Audit — agent-trust-hub — business-plan-generator