renewal-tracker

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Data Access and Processing: The skill accesses a configuration file at ~/.claude/plugins/config/claude-for-legal/commercial-legal/renewal-register.yaml which contains business-sensitive information, including contract values, counterparty names, and business owner contact details. This access is central to the skill's purpose of tracking renewals.
  • External System Integration (Indirect Prompt Injection Surface): The skill possesses the capability to ingest data from external sources such as Contract Lifecycle Management (CLM) systems and DocuSign metadata (Mode 3).
  • Ingestion points: Data is retrieved via MCP tool queries for 'Active' agreements and DocuSign envelopes.
  • Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions when processing external metadata strings.
  • Capability inventory: The agent has the ability to read and write to the local file system and execute connected MCP tools for external queries.
  • Sanitization: There is no specific mention of sanitizing or escaping metadata retrieved from these external platforms. This creates a potential surface where malformed or intentionally crafted metadata in an external system could influence agent behavior, a standard consideration when processing untrusted external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:00 PM
Security Audit — agent-trust-hub — renewal-tracker