swift-expert

Fail

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL (https://jeffallan.github.io/claude-skills/skills/language/swift-expert/) that is identified as a malicious site by automated reputation scanners.
  • [METADATA_POISONING]: The skill manifest file (SKILL.md) has been flagged by file reputation scanners for having malicious characteristics (FileRepMalware).
  • [INDIRECT_PROMPT_INJECTION]: The skill's architecture analysis phase ingests user-provided project metadata and dependency lists, creating a surface where adversarial instructions in project files could be ingested. • Ingestion points: Architecture Analysis phase in SKILL.md. • Boundary markers: None identified. • Capability inventory: Code generation and execution of swift toolchain commands (swift build, swift test). • Sanitization: No verification or sanitization of project metadata is specified.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 6, 2026, 11:36 AM
Security Audit — agent-trust-hub — swift-expert