campaign-deck-builder

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill processes user-supplied information to generate a PowerPoint deck. This process involves taking external input and placing it into a template, which is a common pattern for document automation.
  • Ingestion points: User interview answers are captured via SKILL.md and stored in a local answers.json file.
  • Boundary markers: Data is structured within a JSON object before being processed by the script, providing clear separation between data and instructions.
  • Capability inventory: The scripts/build_campaign.py script utilizes the python-pptx library to write to the file system and generate the presentation.
  • Sanitization: The script converts inputs to strings during the token replacement process; however, the potential for rendering untrusted content within a document is an inherent consideration for this type of workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:55 PM
Security Audit — agent-trust-hub — campaign-deck-builder