blog-image-prompt

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes external, untrusted blog content or file paths provided via arguments.
  • Ingestion points: Reads blog post content or files via the $ARGUMENTS parameter in SKILL.md.
  • Boundary markers: None identified; the skill directly incorporates the input into its analysis phase.
  • Capability inventory: Performs file system writes to the ._tmp/images/ directory.
  • Sanitization: No specific sanitization or instruction-ignoring delimiters are present to handle malicious commands embedded within the blog content.
  • [EXTERNAL_DOWNLOADS]: The skill includes a reference to Google AI Studio for image generation. This is a well-known service and is considered a safe external reference.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:44 AM