expansion-kickoff

Warn

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive local file paths to read jurisdictional data.
  • Evidence: Loads jurisdictional footprints and escalation tables from ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md.
  • [COMMAND_EXECUTION]: The skill performs file system write operations in protected configuration directories.
  • Evidence: Creates and updates persistent tracker files at ~/.claude/plugins/config/claude-for-legal/employment-legal/expansion-[slug].yaml.
  • [DATA_EXFILTRATION]: The skill processes untrusted data which creates a surface for indirect prompt injection.
  • Ingestion points: Reads external configuration from CLAUDE.md and content from the international-expansion reference skill.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when loading these files.
  • Capability inventory: The skill has file read and write capabilities on the local file system.
  • Sanitization: No evidence of validation or sanitization of the content loaded from the configuration files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 3, 2026, 03:57 PM
Security Audit — agent-trust-hub — expansion-kickoff