Skills
skills/marcusrbrown/systematic/report-bug-ce/Gen Agent Trust Hub

report-bug-ce

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands to gather system and environment data, specifically uname -a, opencode --version, codex --version, and the GitHub CLI gh issue create.
  • [DATA_EXFILTRATION]: Diagnostic information, including OS details and plugin version data retrieved from local configuration files such as ~/.config/opencode/plugins/installed_plugins.json, is transmitted to the author's GitHub repository at marcusrbrown/systematic.
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface. Ingestion points: User responses to questions regarding bug descriptions and reproduction steps (SKILL.md). Boundary markers: Absent. Capability inventory: Command execution (gh, uname) and local file reading (SKILL.md). Sanitization: Absent; user-provided text is interpolated directly into the body of the gh issue create command.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 03:11 PM
Security Audit — agent-trust-hub — report-bug-ce