deploy-checklist

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest data from external connectors if available, which introduces a surface for indirect prompt injection.\n
  • Ingestion points: The skill instructions indicate it can pull release diffs, PR change lists, and build/test status from source control and CI/CD systems (SKILL.md).\n
  • Boundary markers: There are no explicit delimiters or instructions for the agent to distinguish between its hardcoded logic and the external data it retrieves.\n
  • Capability inventory: The skill is restricted to using the 'Read', 'Glob', and 'Grep' tools, which significantly limits the potential for an attacker to escalate privileges or perform destructive operations through an injection.\n
  • Sanitization: No sanitization or validation steps are defined for the data pulled from external sources before it is processed or presented to the user.\n- [NO_CODE]: The skill consists entirely of instructional markdown and does not include any scripts, executables, or complex logic that would require runtime code analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:50 AM
Security Audit — agent-trust-hub — deploy-checklist