swift-cognitive-complexity

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external Swift code provided by users, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill reads file paths or code snippets provided in the $ARGUMENTS field using the Read tool.
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the processed code, such as those hidden in comments.
  • Capability inventory: The agent has access to tools including Bash and Edit, which allow for shell command execution and file system writes.
  • Sanitization: The skill does not implement any validation or sanitization of the input code before it is analyzed or refactored.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:40 PM
Security Audit — agent-trust-hub — swift-cognitive-complexity