gamma-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting data from the Gamma API, which represents an indirect prompt injection surface.
- Ingestion points: API responses from
gamma.listThemes(),gamma.listFolders(), and presentation data inSKILL.mdandreferences/implementation.md. - Boundary markers: Absent from the provided code snippets.
- Capability inventory: The skill utilizes
Read,Write, andEdittools as defined in the frontmatter. - Sanitization: No explicit sanitization of API data is shown, as the code focuses on performance metrics and caching logic.
- [EXTERNAL_DOWNLOADS]: The skill references and provides implementation examples for well-known and established libraries including
p-limitandnode-cache. - [DATA_EXFILTRATION]: The skill interacts with the legitimate Gamma API (
public-api.gamma.app). It includes explicit instructions to avoid including source content, viewer data, or tokens in tuning receipts, and correctly implements secret management using environment variables.
Audit Metadata