google-slides

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external presentations and speaker notes.
  • Ingestion points: Presentation structure and slide content are read via the Google Slides API as described in SKILL.md.
  • Boundary markers: The instructions lack delimiters or warnings to ignore instructions embedded within the retrieved slide data.
  • Capability inventory: The skill uses curl for network operations and writes temporary files to /tmp/google_slides_request.json.
  • Sanitization: No data sanitization or validation is described before processing presentation content.
  • [DATA_EXFILTRATION]: The skill communicates with the official Google Slides API (slides.googleapis.com) using the $GOOGLE_DRIVE_TOKEN environment variable. This interaction targets a well-known service and aligns with the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill suggests using the okou CLI tool for troubleshooting connector settings and verifying API connectivity. This involves executing local commands to inspect environment variables and network status.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:56 PM
Security Audit — agent-trust-hub — google-slides