triage

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of high-level instructions for request classification and does not contain any executable scripts, shell commands, or network operations. No indicators of prompt injection, data exfiltration, or obfuscation were found.
  • [PROMPT_INJECTION]: As a triage utility, the skill is designed to process untrusted data from external sources (Slack, Linear, bug reports). This constitutes a standard surface for indirect prompt injection; however, the skill's logic is restricted to classification and recommendation, providing a safe layer of human-in-the-loop or supervised routing before any implementation skills are invoked.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:05 PM
Security Audit — agent-trust-hub — triage