metrics-dashboard
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing external, untrusted data.
- Ingestion points: The
SKILL.mdfile instructs the agent to read user-provided documents, including dashboards, analytics data, and OKRs. - Boundary markers: The prompt lacks explicit delimiters or warnings to the agent to disregard instructions that might be contained within the external files.
- Capability inventory: The skill's capabilities are restricted to generating and saving markdown documents; it does not utilize high-risk tools such as shell execution, network requests, or sensitive file system access.
- Sanitization: No sanitization, filtering, or validation is performed on the data ingested from user files.
Audit Metadata