expansion-kickoff

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Data Processing Surface: The skill generates expansion trackers by combining user-provided country names with data from a jurisdictional configuration file. This creates a surface where external inputs are processed and written to the file system. * Ingestion points: The skill reads from ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md and accepts a [country name] argument. * Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the embedded jurisdictional data as untrusted. * Capability inventory: The skill utilizes file reading and writing capabilities within the ~/.claude/plugins/config/ directory. * Sanitization: The instructions do not specify validation or escaping for the country name input or the jurisdictional footprint data before they are used to create or update tracker files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:01 PM