slides-grab-card-news

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes slide data from user-specified local directories.
  • Ingestion points: Untrusted slide content is ingested via the path provided to the --slides-dir argument throughout the workflow.
  • Boundary markers: The skill does not define specific delimiters or include instructions for the agent to ignore potentially malicious commands embedded within the slide files.
  • Capability inventory: The skill utilizes the slides-grab CLI to execute validation, viewing, and multi-format export operations (PNG, PDF, PPTX).
  • Sanitization: There are no explicit validation or sanitization steps defined for the source content before it is processed by the agent or the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 04:16 PM