growth-engine

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses the shell command cut to extract data from a local JSONL file and curl to send notifications to an external service. It also references a hardcoded absolute local filesystem path /Users/kameronkales/planfi-app in the workflow configuration.
  • [DATA_EXFILTRATION]: Sends project-specific status updates, including prospect counts and report paths, to a Discord webhook. The webhook URL is retrieved from the agent's memory/configuration rather than being hardcoded.
  • [EXTERNAL_DOWNLOADS]: Triggers a workflow that performs automated web searches to identify and qualify potential business prospects.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from external web searches and processes it without explicit sanitization or boundary markers.
  • Ingestion points: growth/prospects.jsonl and results from the growth-engine workflow (which performs WebSearches).
  • Boundary markers: Absent in the workflow invocation and file writing steps.
  • Capability inventory: File writes (growth/prospects.jsonl, growth/runs/, growth/monetization-playbook.md), shell execution (cut, curl), and workflow execution.
  • Sanitization: None identified in the instructions for processing researched data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 04:50 PM
Security Audit — agent-trust-hub — growth-engine