swift-expert

Fail

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes documentation links to a blacklisted domain (jeffallan.github.io/claude-skills/), which is identified as malicious by URL reputation scanners.
  • [METADATA_POISONING]: The SKILL.md file itself is flagged with a malicious reputation score (FileRepMalware), indicating it is associated with known malicious activity or signatures.
  • [COMMAND_EXECUTION]: The instructions command the agent to run build operations (swift build, swift test) which, in the context of a confirmed malicious file reputation, facilitates the potential execution of malicious build-time scripts or exploits in the local development environment.
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 5, 2026, 11:39 AM
Security Audit — agent-trust-hub — swift-expert