skills/ton-connect/kit/ton-nfts/Gen Agent Trust Hub

ton-nfts

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the retrieval and display of NFT metadata, which constitutes an indirect prompt injection surface.\n
  • Ingestion points: Untrusted external data enters the agent context via the output of the get_nfts, get_nfts_by_address, and get_nft tools as defined in SKILL.md.\n
  • Boundary markers: The skill lacks explicit boundary markers or instructions to the model to ignore potential commands embedded in the retrieved metadata.\n
  • Capability inventory: The skill has access to the send_nft tool, allowing it to perform asset transfers based on model decisions.\n
  • Sanitization: No sanitization, validation, or filtering of the NFT metadata is mentioned or implemented before the data is presented to the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 09:14 AM