process-transformation-story

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to access and analyze external media (MP4, JPG) and web content from goodcase.ai and x.com (Twitter) to ground the visual style of the generated prompts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of prompt excerpts and summaries from references/cases.md to influence output generation. This is mitigated by a strict 'Reference Contract' (Preserve/Replace/Avoid) and a verification checklist.
  • Ingestion points: references/cases.md contains external prompt excerpts and descriptions.
  • Boundary markers: The 'Required evidence gate' and 'Output contract' in SKILL.md define strict boundaries for how reference data is used.
  • Capability inventory: Uses browser, image, and video tools to inspect remote assets.
  • Sanitization: The 'Verification' section requires the agent to distinguish observed evidence from its own recommendations and labels results as 'prompt-grounded' if media is inaccessible.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 12:00 AM