post-mortem
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized activities were detected. The skill is strictly instructional and follows safe design principles.
- [DATA_EXFILTRATION]: While the skill mentions using the JIRA API to post reports, it mandates a human-in-the-loop sign-off process, which mitigates risks of unauthorized data transmission or automated exfiltration.
- [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety guidelines or override system prompts.
Audit Metadata