presentation-creation

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted external content.
  • Ingestion points: Source material includes documents, outlines, and meeting notes as specified in the workflow and usage sections of SKILL.md.
  • Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within the source documents.
  • Capability inventory: The skill generates diverse output formats including reveal.js (HTML) and python-pptx scripts, which can act as vectors for injection.
  • Sanitization: The instructions do not define methods for sanitizing or escaping content before it is included in the generated output.
  • [COMMAND_EXECUTION]: The skill instructions specify the generation of python-pptx scripts based on user-provided content. This involves the creation of executable code which could be manipulated if the source material contains malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 08:23 AM
Security Audit — agent-trust-hub — presentation-creation