event-driven-architecture
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to check for companion skills by listing contents of local skill directories (e.g., ~/.claude/skills/) using the ls command. This is used for environment discovery to assist the user with setup.- [PROMPT_INJECTION]: The skill includes a stylistic instruction to prefix responses with a specific emoji (🧢). Additionally, the skill's architecture for processing events presents a surface for indirect prompt injection. 1. Ingestion points: Event data payloads processed in aggregate reconstruction and projection logic (SKILL.md, event-sourcing-patterns.md). 2. Boundary markers: None provided in example code. 3. Capability inventory: Database writes and shell execution (ls). 4. Sanitization: No explicit sanitization of event data is mentioned in the educational snippets.- [EXTERNAL_DOWNLOADS]: The skill recommends installing companion packages from the author's repository (AbsolutelySkilled) using the npx utility, which is the standard distribution mechanism for this platform.
Audit Metadata