google-slides

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests presentation data and speaker notes from the Google Slides API, which is an external and untrusted source. This content could be crafted to include malicious instructions aimed at manipulating the agent's actions.
  • Ingestion points: Presentation structure and slide content are fetched from slides.googleapis.com using curl in several commands throughout SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructional warnings to prevent the agent from following instructions embedded within the retrieved slide data.
  • Capability inventory: The skill has the ability to perform network operations (GET/POST) via curl and write temporary JSON configuration files to the /tmp directory.
  • Sanitization: No explicit validation, escaping, or sanitization of the content fetched from the Google Slides API is described before the data is processed or used in subsequent operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:07 PM
Security Audit — agent-trust-hub — google-slides