GordenSuperPPTSkill

Pass

Audited by Gen Agent Trust Hub on Jun 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill coordinates the execution of local Python scripts such as compose_pptx.py, chroma_key.py, and slice_grid.py. These scripts are used for assembling PowerPoint files and processing images as part of the orchestration workflow.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its data processing requirements.
  • Ingestion points: User-supplied themes and content are used to generate prompts (SKILL.md), and OCR text is extracted from images (references/pipeline.md).
  • Boundary markers: There are no explicit markers or instructions to delimit untrusted data from system instructions.
  • Capability inventory: The skill possesses the capability to write files to the local system, call the imagegen tool, and execute local Python scripts.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of user-provided content or OCR results before they are processed by the agent or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 8, 2026, 07:48 AM
Security Audit — agent-trust-hub — GordenSuperPPTSkill