products

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute internal utility scripts such as sync-portfolio.sh and project-status.sh found within the plugin's directory. These scripts are used for routine data synchronization and project auditing.
  • [EXTERNAL_DOWNLOADS]: Automatically triggers subagents to perform web research on provided URLs to extract product offerings, which is an intended discovery feature of the skill.
  • [PROMPT_INJECTION]: Ingests and processes data from user-uploaded documents and web research results, which presents a surface for indirect prompt injection.
  • Ingestion points: Analyzes content in the uploads/ directory and results from subagent-driven web research.
  • Boundary markers: No explicit markers or warnings are used to distinguish processed data from the agent's instructions.
  • Capability inventory: Includes the ability to write/edit local project files and execute internal shell scripts.
  • Sanitization: No validation or sanitization logic is specified for the external data ingested.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:51 PM
Security Audit — agent-trust-hub — products