superset-feedback
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various commands using the
supersetandgh(GitHub) CLI tools to gather environment context and submit feedback. These operations are essential to the skill's functionality. - [DATA_EXFILTRATION]: The skill transmits user-generated reports and environment metadata to external destinations (
support@superset.shor thesuperset-sh/supersetrepository). This is the intended purpose of the skill; it includes safeguards such as requiring user approval for the final draft and specifically asking for consent before including potentially sensitive application logs. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate feedback reports. It mitigates the risk of command injection by explicitly instructing the agent to use shell heredocs with quoted delimiters (
<<'EOF') or temporary files when passing content to CLI tools, preventing the shell from interpreting the data as executable code.
Audit Metadata