event-volunteers
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of documentation and instructional content. No executable code, scripts, or suspicious commands were found in the skill files or references.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow involving the processing of untrusted external data, specifically a 'run of show' and 'code of conduct' document (SKILL.md, Workflow steps 1 and 2). 1. Ingestion points: User-provided schedule documents and interview responses. 2. Boundary markers: None explicitly defined in the prompt instructions. 3. Capability inventory: Limited to text generation; no access to subprocesses, shell execution, network operations, or file system writes. 4. Sanitization: None mentioned, but the lack of dangerous capabilities mitigates the risk.
- [METADATA_POISONING]: The metadata fields, including the author and versioning, are consistent with the skill's purpose and do not contain deceptive instructions.
Audit Metadata