inkblot-jira-ticket

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill implements a strict 'hard rule' prohibiting the inclusion of Personally Identifiable Information (PII) or Protected Health Information (PHI) in Jira tickets. It explicitly instructs the agent to redact identifying details from screenshots, logs, and stack traces.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: References to external domains (e.g., inkblottherapy.atlassian.net, practice.inkblottherapy.com, api.inkblottherapy.com) are restricted to the organization's own infrastructure and are consistent with the skill's primary purpose.
  • [PROMPT_INJECTION]: The instructions focus on structural formatting and data privacy. No patterns of jailbreaking, safety filter bypass, or instruction override were detected.
  • [REMOTE_CODE_EXECUTION]: The skill does not contain any shell commands, remote script downloads, or package installation instructions.
  • [NO_CODE]: This skill consists entirely of markdown-based instructions for the agent and does not include any accompanying scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:15 PM
Security Audit — agent-trust-hub — inkblot-jira-ticket