luma-event-attendees
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill fetches event metadata, host information, and guest bios from Luma event pages (
scripts/apify_client.py) and via the Apify API (scripts/apify_client.py). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its internal logic and the untrusted external content it processes.
- Capability inventory: The skill has the capability to write files to the local file system using the
--outputparameter and perform network operations to Luma and Apify domains. - Sanitization: The skill retrieves and stores external content (names, bios, and descriptions) as raw strings without sanitizing the text for potential natural language instruction injections.
Audit Metadata