slide-deck
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to generate and run a Python script using the
python-pptxlibrary to create binary files (.pptx). This is the primary mechanism for file generation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it transforms untrusted user data (docs, notes, outlines) into script logic without explicit sanitization or structural boundaries.
- Ingestion points: User-provided "content" such as outlines, documents, or notes entering the context via the "Required Inputs" section in
SKILL.md. - Boundary markers: Absent; the instructions do not specify the use of delimiters or provide warnings to ignore embedded instructions within the user-provided content.
- Capability inventory: The skill is designed to write and execute Python code and perform file-write operations to create
.pptxfiles (SKILL.md). - Sanitization: Absent; the skill does not define any validation, filtering, or escaping steps for user input before it is interpolated into the generated Python script.
Audit Metadata