pitch-deck-visuals

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill employs a remote Python executor (infsh/python-executor) to generate visualizations such as traction charts and market size diagrams. The execution is limited to static Python templates using the matplotlib library for rendering plots to image files.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official installation guides and documentation hosted on GitHub (inference-sh/skills). These references are necessary for setting up the required CLI environment and do not involve untrusted code execution.
  • [COMMAND_EXECUTION]: Usage of the belt CLI tool is restricted via the allowed-tools configuration in the YAML frontmatter. The commands performed, such as logging in and running platform-specific applications, are standard operations for interacting with the vendor's services.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines JSON schemas for inputting data into remote applications (e.g., HTML strings for image conversion). While this creates a potential ingestion surface for untrusted data, the skill uses these structures for legitimate data presentation and visualization tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — pitch-deck-visuals