analyze-dashboard
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for business data analysis. All tools used (e.g., Amplitude:get_dashboard, Amplitude:query_charts) are specific to the vendor and align with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user feedback, which represents a potential attack surface.
- Ingestion points: Customer feedback quotes and mentions are retrieved via Amplitude:get_feedback_mentions as described in Step 4 of SKILL.md.
- Boundary markers: There are no explicit markers or instructions for the agent to ignore instructions that might be embedded in the feedback text.
- Capability inventory: The skill's capabilities are restricted to data retrieval and text synthesis. It does not perform file writes, network operations to non-whitelisted domains, or shell command execution.
- Sanitization: The skill does not perform sanitization of the retrieved feedback data before processing.
Audit Metadata