skills/oimiragieo/agent-studio/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'python-pptx' package from standard Python package registries.
  • [COMMAND_EXECUTION]: Uses the 'Bash' tool to manage dependencies and execute Python scripts for presentation generation.
  • [PROMPT_INJECTION]: The skill processes external data to generate slide content through the 'claude_output_to_slides' function in 'SKILL.md'. This represents an indirect prompt injection surface. Ingestion points: Data enters via the 'slide_data' argument in the 'claude_output_to_slides' function in 'SKILL.md'. Boundary markers: None present; data is directly interpolated into slide shapes. Capability inventory: Includes file writing ('prs.save' in 'SKILL.md'), image reading ('add_picture' in 'SKILL.md'), and shell command execution ('pip install' in 'SKILL.md'). Sanitization: No explicit sanitization or validation of input strings is performed before they are added to the presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 08:27 AM
Security Audit — agent-trust-hub — pptx