devops-platform-engineering

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by processing untrusted user data in its automation workflows.
  • Ingestion points: Untrusted user input enters the agent context through the parameters properties in Backstage Software Templates defined in SKILL.md (e.g., serviceName, description on lines 150-175).
  • Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore or treat user-provided strings as data rather than instructions.
  • Capability inventory: The skill possesses the ability to execute repository publishing via publish:github and register entities in a live catalog via catalog:register as shown in SKILL.md (lines 184-194).
  • Sanitization: No input validation or escaping mechanisms are described for the interpolated content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:15 PM
Security Audit — agent-trust-hub — devops-platform-engineering