grafana-dashboard-optimize
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill. The instructions focus on best practices for observability and SRE methodologies.
- [PROMPT_INJECTION]: The skill processes untrusted external dashboard files, which represents an indirect prompt injection surface. The risk is minimal as the skill generates configuration snippets rather than executing commands. Ingestion points: Dashboard content and local configuration files are read into context (SKILL.md, Phase 1). Boundary markers: No delimiters are specified for the audited data. Capability inventory: Generation and modification of Jsonnet code snippets (SKILL.md, Step 4). Sanitization: No mention of filtering instructions embedded in dashboard metadata or comments.
Audit Metadata