event-speaker-experience
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing untrusted data from speakers, such as talk proposals and personal details, which creates an indirect prompt injection surface. However, the risk is minimal as the skill does not utilize any high-risk capabilities. * Ingestion points: Speaker bios, headshots, and email communications (SKILL.md, references/material-collection-and-deadlines.md). * Boundary markers: Not explicitly defined for external inputs. * Capability inventory: No subprocess execution, file-writing, or network tools are present in the skill's instructions. * Sanitization: No explicit sanitization or filtering of external content is described.
- [DATA_EXPOSURE]: The skill's workflow manages sensitive Personally Identifiable Information (PII), including travel documents and payment details. It addresses this by providing clear instructions for a 'retention pass' to ensure sensitive data is deleted after the event concludes, adhering to privacy standards.
Audit Metadata