github-dashboard
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the official GitHub CLI (
gh) to perform read-only operations for gathering dashboard data. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (GitHub notifications, PR titles, and issue descriptions). While the skill's primary function is summarization, malicious content within these GitHub resources could theoretically attempt to influence the agent's output.
- Ingestion points: Data is ingested from GitHub via
gh api notifications,gh pr list, andgh issue listcommands. - Boundary markers: The instructions do not define explicit delimiters to isolate external content from the agent's instructions.
- Capability inventory: The skill is limited to reading data and generating a summary; it does not contain capabilities for file writing, network exfiltration, or secondary script execution based on the ingested data.
- Sanitization: There is no evidence of specific filtering or sanitization of the fetched GitHub metadata before processing.
Audit Metadata