baoyu-cover-image

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from user-provided articles or text. It extracts titles, summaries, and keywords to populate a generation prompt template without sanitization.
  • Ingestion points: Input article files or pasted text processed in Step 1 of the SKILL.md workflow.
  • Boundary markers: The prompt template in references/workflow/prompt-template.md uses headers but does not include explicit delimiters or instructions to ignore embedded commands within user data.
  • Capability inventory: Access to local file systems (read/write) for saving prompts and references, and execution of image generation tools.
  • Sanitization: There is no evidence of validation or filtering of user-supplied text before its inclusion in the generation prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:32 AM