github-dashboard
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the official
ghCLI tool to interact with GitHub services. - [DATA_EXFILTRATION]: The skill accesses GitHub account data including notifications, PR statuses, and issue details. This is the primary intended function of the dashboard skill and does not involve unauthorized transmission to third parties.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from GitHub. 1. Ingestion points: Output from
gh api notifications,gh pr list, andgh issue listin SKILL.md. 2. Boundary markers: None. 3. Capability inventory: The skill is limited to generating a summary report and suggest priorities. 4. Sanitization: None. The risk is minimal as the agent only reads and summarizes the content without performing automated write actions.
Audit Metadata