headshots-from-photos

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, such as HTTPS photo URLs and local file uploads, to create identity references for image generation.
  • Ingestion points: Processes user-supplied HTTPS URLs and local media files as described in the identity reference section of SKILL.md.
  • Boundary markers: The skill does not explicitly define delimiters or instructions to ignore potential adversarial content embedded within the image data (e.g., visual prompt injection).
  • Capability inventory: The skill utilizes tools such as create_reference, generate_images, and run_template to interact with the Astria API infrastructure.
  • Sanitization: No specific sanitization or filtering of external media content is outlined in the instructions; however, this is a standard functional requirement for the skill's primary purpose.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of user-provided media from external HTTPS URLs to create identity references. This behavior is consistent with the intended functionality of the service and uses vendor-provided tools (astria-api).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 07:36 PM