adapting-formats

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes user-supplied images and URLs, creating an attack surface where malicious instructions embedded in the source data could influence the agent's content generation process.
  • Ingestion points: User-provided ad images and URLs (SKILL.md, Step 1).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the analyzed content.
  • Capability inventory: The skill uses image_analysis to read content and image_generate to create new images based on that content (SKILL.md, Steps 2 and 7).
  • Sanitization: There is no evidence of sanitization or validation of the text extracted from the source images before it is used in the prompt construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:23 PM
Security Audit — agent-trust-hub — adapting-formats