devops-automation

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by ingesting and processing untrusted data from various external triggers.
    • Ingestion points: The skill processes untrusted input from GitHub webhooks (commit messages, PR titles), Jira tickets, Slack requests, and external monitoring alerts (Prometheus, Datadog) as seen in the CI/CD and Incident Management templates in SKILL.md.
    • Boundary markers: The notification and communication templates do not implement boundary markers or instructions to the agent to disregard embedded commands in the external data (e.g., {pr_title}, {commit_message}).
    • Capability inventory: The skill is configured to use high-privilege tools including github_api, jenkins_trigger, aws_cli, and kubernetes_api (SKILL.md frontmatter).
    • Sanitization: There is no evidence of sanitization or strict schema validation for the external data before it is used in automation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:46 PM
Security Audit — agent-trust-hub — devops-automation