ppt-creator
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script
scripts/chartkit.pyto process user-provided data and generate charts. This script is called via a command line interface using parameters derived from external inputs. - [PROMPT_INJECTION]: The skill processes untrusted user data—including documents, CSV files, and tables—to generate slide content and charts. This represents an indirect prompt injection surface where malicious instructions embedded in the input data could influence the agent's behavior during generation or refinement.
- Ingestion points: User data and files are ingested in Stage 0 (Archive Input), Stage 3 (Outline & Slide Titles), and Stage 4 (Evidence & Charts).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when processing user-provided content.
- Capability inventory: The skill executes local scripts (
scripts/chartkit.py) and performs file writes to the/output/directory. - Sanitization: There are no mentioned mechanisms for sanitizing or validating external input before it is used for prompt interpolation or script execution.
Audit Metadata