office-powerpoint

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run to execute Python scripts located within its own directory (~/.kiro/skills/office-powerpoint/scripts/). This is an expected mechanism for executing the skill's functionality.
  • [DATA_EXPOSURE]: The skill processes user-provided PowerPoint and Markdown files. It does not access sensitive system files or credentials.
  • [REMOTE_CODE_EXECUTION]: All code is local to the skill's scripts directory. There are no patterns of downloading and executing remote code.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external files (.pptx and .md) which could contain adversarial instructions, it acts as a data transformer. It does not interpret the content as instructions for the agent, but rather as data to be formatted into slides or markdown text. The use of clear markdown markers ('#', '##', '---') helps maintain data/instruction boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:29 PM
Security Audit — agent-trust-hub — office-powerpoint