add-event-handler
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves the ingestion and processing of external event schemas and payloads, which is an inherent attack surface for indirect prompt injection if those sources are compromised.
- Ingestion points: Event payloads and external schemas (Avro, Protobuf, JSON Schema) mentioned in the implementation process (SKILL.md).
- Boundary markers: The skill enforces the use of the CloudEvents 1.0 standard and schema registries to maintain structured data boundaries.
- Capability inventory: The skill is permitted to use file system tools (read_file, write_file, edit_file) and execute shell commands (execute_command) as defined in the frontmatter.
- Sanitization: Instructions include explicit guardrails (ASI01, ASI05) that mandate strict schema validation and reject logic construction from unvalidated external content.
Audit Metadata