NYC

google-slides

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection because it reads untrusted slide content and has the capability to modify presentations. \n
  • Ingestion points: The get-text command extracts all text from potentially attacker-controlled Google Slides (File: SKILL.md). \n
  • Boundary markers: No delimiters or safety instructions are defined to separate ingested content from system instructions. \n
  • Capability inventory: The skill has extensive write permissions including create, add-slide, replace-text, and batch-update (File: SKILL.md). \n
  • Sanitization: No evidence of data sanitization or input validation for presentation content. \n- [NO_CODE] (SAFE): The core implementation scripts (scripts/auth.py and scripts/slides.py) are referenced but not included in the provided files. Analysis is based on the documentation and requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:53 AM