ghostty-to-termy

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Ghostty configuration files and instructs the agent to review the resulting compatibility report. This creates a surface for indirect prompt injection if a source file contains malicious instructions within configuration values.\n
  • Ingestion points: The agent ingests data from the compatibility report generated by the conversion script from user-provided Ghostty configs.\n
  • Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore potentially malicious instructions embedded within the reported configuration values.\n
  • Capability inventory: The agent has capabilities for script execution, file reading, and file system modification.\n
  • Sanitization: While the script validates many settings, it reflects unsupported or warning-level keys and values into the report JSON, providing a vector for arbitrary text to reach the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 11:35 PM
Security Audit — agent-trust-hub — ghostty-to-termy