oh-my-ppt-chart
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate the ingestion of data (labels and datasets) into chart configurations, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: The
data.labelsanddata.datasetsproperties within the configuration object passed toPPT.createChart(documented in SKILL.md and references/chart.md). - Boundary markers: Absent. The instructions do not specify the use of delimiters or provide warnings to the agent to disregard instructions that might be embedded in the provided data.
- Capability inventory: The skill's primary capabilities are limited to DOM manipulation and UI rendering via a specialized API. It does not request file system access or network operations.
- Sanitization: Absent. The instructions do not prescribe sanitization, escaping, or validation of the data before it is interpolated into the script blocks.
- [DYNAMIC_EXECUTION]: The skill provides templates for the AI agent to generate and execute JavaScript code at runtime for chart initialization.
- Evidence: The skill provides boilerplate code for
<script>tags that usedocument.addEventListener('DOMContentLoaded', ...)to invokePPT.createChart(SKILL.md, references/chart.md).
Audit Metadata