prompt-enhancer
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFE
Full Analysis
- [IND I R E C T_PROMPT_INJ E C T I O N]: The skill in g e s t s un t r u s t e d dat a from us e r requi r e m e n t s an d stor e s i t i n a JSON ar t i f a c t in t e n d e d for pro c e s s i n g by dow n s t r e a m skil l s. Whil e the skill it s e l f is benig n, it crea t e s a vu l n e r a b i l i t y sur f a c e if sub s e q u e n t skil l s do not pro p e r l y san i t i z e or val i d a t e the in h e r i t e d con t e x t.
- In g e s t i o n poin t s: Us e r requi r e m e n t s an d sub s e q u e n t re s p o n s e s to clarif y i n g que s t i o n s prov i d e d via the
As k U s e r Q u e s t i o ntool. - Bou n d a r y mar k e r s: No ne pre s e n t; the ar t i f a c t doe s not us e spe c i f i c del i m i t e r s or di r e c t i v e s to ig n o r e in t e r p ol a t e d in s t r u c t i o n s.
- Cap a b i l i t y in v e n t or y: The skill ha s
Wr i t eper m i s s i o n s to crea t e ar t i f a c t s an d us e sAs k U s e r Q u e s t i o nto in g e s t ex t e r n a l con t e n t. - San i t i z a t i o n: The skill doe s not ex p l i c i t l y san i t i z e or fil t e r us e r-prov i d e d tex t befo r e stor i n g it in the ou t p u t ar t i f a c t.
Audit Metadata