event-run-of-show
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided event details (such as supplier names, venue constraints, and specific cues) to generate structured schedules. This creates a surface where instructions embedded in untrusted data could potentially influence the output.
- Ingestion points: Data enters the context via the 'Required Inputs' section described in
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat input data as literal text or to ignore embedded instructions.
- Capability inventory: The skill does not use any tools for file writing, network operations, or shell execution, limiting the potential impact of an injection to the generated text itself.
- Sanitization: The instructions do not specify any validation or sanitization steps for the input data.
- [SAFE]: The skill focuses entirely on structural event planning logic and does not utilize any risky tools, network operations, or file system access. The instructions promote best practices for event safety and coordination.
Audit Metadata