strk20-anonymizer-contracts

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's purpose is to audit and write Cairo smart contracts, which necessitates processing untrusted code provided by users. This creates a surface for indirect prompt injection attacks.
  • Ingestion points: External Cairo contract code provided for auditing or review.
  • Boundary markers: The skill does not define delimiters or specific instructions to the agent to ignore instructions embedded within the provided code.
  • Capability inventory: The agent can generate and audit executable contract logic.
  • Sanitization: No input validation or sanitization steps are defined for the source code being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 10:11 PM
Security Audit — agent-trust-hub — strk20-anonymizer-contracts