powerpoint

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several local scripts (html2pptx.js, scripts/thumbnail.py, scripts/rearrange.py, and scripts/replace.py) to perform PowerPoint operations. These scripts are invoked with specific arguments to generate thumbnails, rearrange slides, and inject text content, which is consistent with the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, such as converting reports into presentations or auditing existing decks. While this creates a surface for indirect prompt injection from untrusted files, the instructions do not include any patterns that attempt to bypass safety filters or execute malicious commands based on that data.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill instructions manage slide content and layout locally and do not contain any network operations or instructions to exfiltrate data to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 08:36 AM
Security Audit — agent-trust-hub — powerpoint