superset-feedback

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local CLI tools including 'superset' (vendor-specific) and 'gh' (GitHub official CLI) to collect environment metadata and manage issue reporting.
  • [DATA_EXFILTRATION]: Information such as Superset version, OS type, and user identity is collected and transmitted to the vendor (superset-sh) or GitHub. This is appropriate for the skill's purpose, and more sensitive data like log files require explicit user confirmation before attachment.
  • [PROMPT_INJECTION]: The skill processes user-supplied feedback into shell commands. It mitigates command injection risks by using quoted heredocs (<<'EOF') for submission bodies, preventing the shell from interpreting the content of the feedback as executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 08:38 AM
Security Audit — agent-trust-hub — superset-feedback