mage-characters
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data including character names, handles, and descriptions which are then used to form prompts for generative models. This creates a potential surface for indirect prompt injection where adversarial content in metadata could influence generation outputs.
- Ingestion points:
SKILL.md(viacreate_characterandcreate_referencetools). - Boundary markers: The instructions do not specify the use of delimiters or protective instructions when interpolating user-provided text into generation prompts.
- Capability inventory: The skill possesses capabilities to create/delete persistent objects and generate media via
generateandseed_audiotools. - Sanitization: No sanitization or validation logic for the content of names or descriptions is described in the skill documentation.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of images and audio files from external, user-supplied URLs to create persistent character and reference assets.
- Evidence:
SKILL.mdinstructions forcreate_characterandcreate_referencetools explicitly support fetching content from HTTPS URLs.
Audit Metadata