test-macos-snapshots

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected. The skill is entirely documentation-based.
  • [NO_CODE]: The skill does not provide any scripts, executables, or automated installation logic.
  • [PROMPT_INJECTION]: The skill involves processing screenshots, which provides an attack surface for indirect prompt injection if the UI displays untrusted text.
  • Ingestion points: Screenshots of macOS windows (SKILL.md)
  • Boundary markers: The 'expectation contract' defined in references/expectation-loop.md serves as a logical boundary by forcing the agent to declare expected state before capture.
  • Capability inventory: Uses tools like Playwright, XCTest, and OS-level capture tools (references/capture-modes.md).
  • Sanitization: None described for image content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 06:59 AM