skills/prathamdby/skills/notify/Gen Agent Trust Hub

notify

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/notify.py to process and send notifications, which is an expected behavior for its stated purpose.
  • [DATA_EXFILTRATION]: Communicates with Discord's API. The script validates that the webhook URL starts with the official Discord prefix, mitigating the risk of data being sent to unauthorized external domains.
  • [CREDENTIALS_UNSAFE]: Manages sensitive webhook URLs in a local file. The instructions correctly emphasize that this file should never be committed to version control, following standard security practices.
  • [PROMPT_INJECTION]: Evaluated for indirect prompt injection risks as it processes external task data. Ingestion points include task work and issue links mentioned in SKILL.md. While no specific boundary markers are used, the script provides capability-level protection through URL validation and length limits.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:54 AM
Security Audit — agent-trust-hub — notify