event-signals

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted web content (such as speaker bios and talk descriptions), which creates a surface for indirect prompt injection where malicious instructions could attempt to influence the agent. 1. Ingestion points: Data from Sessionize, Meetup, Luma, ListenNotes, and Devpost. 2. Boundary markers: The skill uses structured JSON and CSV formats for data storage. 3. Capability inventory: Access to tools including Bash, WebFetch, and Write. 4. Sanitization: Basic HTML cleaning is implemented, though no specific prompt sanitization is present.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a local Python script (scripts/event_signals.py) for API interaction and data processing, which is standard for its intended purpose.
  • [EXTERNAL_DOWNLOADS]: Retrieves configuration and event data from reputable services and public repositories, including GitHub and Sessionize APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:07 PM
Security Audit — agent-trust-hub — event-signals