report

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill instructions define a template-based report generation workflow which is safe and localized to the project directory.
  • [COMMAND_EXECUTION]: Uses the mkdir command to create document directories, which is consistent with the skill's stated purpose of organizing reports.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized privilege escalation was found in the provided files.
  • [SAFE]: The skill has a surface for indirect prompt injection as it processes investigation data. 1. Ingestion points: Summarizing investigation or analysis content (SKILL.md). 2. Boundary markers: None. 3. Capability inventory: Directory creation (mkdir) and file writing. 4. Sanitization: None. Given the limited and benign capabilities, this surface is considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:48 AM