post-mortem

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions are focused on structured documentation and do not contain malicious code, hidden commands, or unauthorized network activity. All external interactions require explicit user confirmation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external technical information which is used to construct payloads for the JIRA API.
  • Ingestion points: Technical details such as root causes and validation steps provided by the user in SKILL.md.
  • Boundary markers: No specific delimiters are used to wrap external content.
  • Capability inventory: Access to the JIRA API for posting comments (POST /rest/api/3/issue/<KEY>/comment).
  • Sanitization: A robust sign-off mechanism requires the user to review and approve the exact payload before any network transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:26 AM
Security Audit — agent-trust-hub — post-mortem