ecc-guide

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several local utility scripts (e.g., node scripts/install-plan.js, node scripts/install-apply.js) and system tools (find, rg, npm) to gather repository information and apply installation plans. These commands are vendor-specific and intended for repository maintenance.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection vulnerabilities because it searches and reads the contents of arbitrary files within the repository using rg and direct file access.
  • Ingestion points: Reads content from skills/, commands/, agents/, and documentation files like README.md.
  • Boundary markers: No explicit delimiters or instructions are used to prevent the agent from obeying instructions found inside the repository files.
  • Capability inventory: The skill allows for the execution of Node.js scripts and shell commands, providing a significant surface for abuse if the agent is hijacked.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the repository files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:19 PM
Security Audit — agent-trust-hub — ecc-guide