writing-release-notes

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses vendor-specific MCP tools and domains (bitwarden.atlassian.net) which are consistent with the identified author. No malicious command execution or data exfiltration patterns were found.
  • [PROMPT_INJECTION]: The skill has a surface area for indirect prompt injection as it processes data from Jira issues and Slack threads which could theoretically contain instructions to alter the release notes output.
  • Ingestion points: Jira issue summaries/descriptions and user-pasted Slack thread text in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Restricted to read-only Atlassian MCP tools.
  • Sanitization: Not explicitly present, though the skill provides strict formatting rules for the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 07:03 PM
Security Audit — agent-trust-hub — writing-release-notes