developer-event-followup
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources, including badge scans, booth notes, and raffle entries. While this ingestion represents a surface for indirect prompt injection, the risk is negligible as the skill lacks high-privilege capabilities such as arbitrary command execution or automated network exfiltration.
- [DATA_EXPOSURE]: The instructions direct the agent to maintain state by storing task-related information in a local memory file named
devrel-context.md. This practice is standard for agent-based workflows and does not expose sensitive system credentials. - [SAFE]: All external references, including links to HubSpot, Google Postmaster Tools, and vendor-owned repositories under the 'samber' namespace, are well-known services or legitimate project resources consistent with the skill's primary purpose.
Audit Metadata