skills/dcoon/agent-kit/dev-plan/Gen Agent Trust Hub

dev-plan

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by reading local repository files and delegating research to external agents. This is a standard and expected behavior for a planning tool and does not indicate malicious intent. \n
  • Ingestion points: SKILL.md identifies repository inspection and external research batches as data entry points. \n
  • Boundary markers: Absent. The instructions do not define specific delimiters for untrusted content. \n
  • Capability inventory: The skill uses search, query, and research tools; it does not perform arbitrary code execution or network exfiltration of sensitive data. \n
  • Sanitization: Absent. Content from files and research is processed without explicit sanitization steps. \n- [NO_CODE]: The skill consists entirely of markdown-based instructions and does not bundle any executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:31 PM