tres-rollup-review

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [Financial Data Access]: The skill retrieves transaction and rollup rule metadata from the TRES Finance platform. This access is performed via a specific MCP connector and is necessary for the skill's purpose of calculating rule impact and validating configurations.
  • [Read-Only Operation]: The instructions explicitly state that the skill does not execute mutations and only computes impact. This constraint limits the skill's functionality to diagnostic analysis, reducing the risk of unintended data modification.
  • [External Data Processing]: The skill ingests data from the TRES Finance API, such as rule names and transaction counts. While this establishes a data ingestion surface where external content enters the agent context, the skill's highly structured output requirements (specific PASS/DROP/FIX verdicts) serve as a behavioral constraint.
  • Ingestion points: Data enters the context via the subTransactionRollupRulePreview and subTransactionRollupRule query results described in SKILL.md.
  • Boundary markers: The skill defines specific output templates for analysis results but does not use explicit delimiters for the raw data ingested from the API.
  • Capability inventory: The skill uses the execute tool for GraphQL queries to interact with the TRES Finance environment.
  • Sanitization: No specific sanitization or escaping routines for the external API data are detailed in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 04:44 AM
Security Audit — agent-trust-hub — tres-rollup-review