analyze-chart
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted customer feedback data to explain chart anomalies. Maliciously crafted feedback could attempt to influence the agent's summary or reasoning.
- Ingestion points: Customer feedback and mentions are ingested via the
Amplitude:get_feedback_insightsandAmplitude:get_feedback_mentionstools in Step 4 (Correlate with Context). - Boundary markers: Absent. The instructions do not define delimiters or specific 'ignore' directives for the agent when processing external feedback content.
- Capability inventory: The skill uses
Amplitude:get_from_url,Amplitude:query_charts,Amplitude:get_experiments, andAmplitude:get_deployments. These tools are focused on data retrieval and do not provide the agent with capabilities to write to the file system or execute shell commands. - Sanitization: Absent. There is no instruction to sanitize, filter, or validate the content of the customer feedback before it is analyzed by the agent.
Audit Metadata