swift-clean-tests

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes user-provided Swift test files to perform quality audits. This creates a surface for indirect prompt injection where malicious instructions embedded in the code or comments could influence the agent's behavior.
  • Ingestion points: Swift test files read via the Read tool or provided in $ARGUMENTS.
  • Boundary markers: None observed in instructions to distinguish data from instructions.
  • Capability inventory: Includes powerful tools like Bash and Edit which can be misused if the agent is successfully injected.
  • Sanitization: None observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:40 PM
Security Audit — agent-trust-hub — swift-clean-tests