analyze-dashboard

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of customer feedback to contextualize dashboard changes.
  • Ingestion points: Data is ingested via the Amplitude:get_feedback_insights and Amplitude:get_feedback_mentions tools as described in Step 4 of SKILL.md.
  • Boundary markers: There are no explicit boundary markers or instructions provided to the agent to treat the feedback content as data rather than instructions.
  • Capability inventory: The skill is primarily analytical and does not possess high-risk capabilities such as arbitrary command execution, network exfiltration to third-party domains, or sensitive file system access.
  • Sanitization: No sanitization, filtering, or validation steps are outlined for the processing of user feedback text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:11 PM
Security Audit — agent-trust-hub — analyze-dashboard