log-virality-issues
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill uses the GitHub CLI (
gh) to list and create issues. This behavior is necessary for the skill's primary purpose and uses standard command-line patterns.\n- [PROMPT_INJECTION] (LOW): Detected surface for Indirect Prompt Injection (Category 8).\n - Ingestion points: Findings from the
/check-viralityprimitive enter the agent's context (SKILL.md).\n - Boundary markers: Absent; findings are interpolated directly into issue templates.\n
- Capability inventory: The skill executes
gh issue createandgh issue listvia the shell (SKILL.md).\n - Sanitization: No explicit sanitization or escaping of the finding data is defined before it is placed into shell commands, though the use of quoted heredocs (
'EOF') in the documentation suggests a degree of awareness regarding shell injection.
Audit Metadata