review-agent-insights
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external AI agent outputs via the Amplitude:get_agent_results tool, creating a surface where instructions embedded in that data could influence the agent's behavior. Ingestion points: Amplitude:get_agent_results in SKILL.md. Boundary markers: None specified in the instructions for separating ingested content. Capability inventory: Limited to read-only Amplitude tools (get_agent_results, get_amplitude_context, get_deployments). Sanitization: None specified. Due to the restricted read-only capabilities and its alignment with the skill's primary purpose, this risk is assessed as safe.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any accompanying scripts, executables, or third-party package dependencies.
Audit Metadata