ppt-pixel-restore
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a utility for visual QA, utilizing standard libraries for image processing and browser automation without malicious intent.- [COMMAND_EXECUTION]: The skill invokes local Python and Node.js scripts (
compare_images.pyanddeck_dom_qa.mjs) to perform image comparisons and layout audits. These executions are scoped to the restoration workflow and do not involve unsanitized user input.- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by processing user-supplied screenshots and URLs. However, the core instructions mitigate this by explicitly stating that text within these sources must be treated as material, not as instructions, thereby protecting the agent from embedded commands.
Audit Metadata