event-speaker-experience
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing data provided by external speakers, such as session titles, talk abstracts, and biographies, which are then used to generate speaker packets and internal records. This creates a surface for indirect prompt injection if a speaker includes malicious instructions within these text fields.
- Ingestion points: Step 1 and Step 3 of the workflow in
SKILL.md(reading acceptance packets and material collection), and the 'Material collection and deadlines' reference file. - Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the AI agent from following instructions potentially embedded within speaker-provided content.
- Capability inventory: The skill is limited to text generation and workflow guidance; it does not utilize shell execution, file system modifications, or network requests directly within its logic.
- Sanitization: The skill does not prescribe any sanitization or validation steps for speaker-provided text before it is processed or displayed.
Audit Metadata