security-dashboard
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from GitHub security alerts (titles, descriptions, and code scanning results) which could be manipulated by external actors to influence agent behavior.
- Ingestion points: GitHub REST API outputs for Dependabot, Code Scanning, and Secret Scanning alerts.
- Boundary markers: Absent. The skill does not define specific delimiters to separate alert content from its own instructions.
- Capability inventory: The skill can execute
gh apicommands to dismiss or resolve alerts and write reports to the local workspace. - Sanitization: No explicit validation or escaping of alert data is mentioned.
- [COMMAND_EXECUTION]: The skill executes the
gh(GitHub CLI) command-line tool to perform its primary functions. - Evidence: Workflow instructions specify using
gh api userand otherghAPI commands to list and manage alerts.
Audit Metadata