work-breakdown

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for work decomposition and dependency mapping. It follows best practices by leveraging specialized code exploration tools to gather context rather than implementing its own arbitrary command execution logic.
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection since it processes untrusted data such as issue descriptions and source code.
  • Ingestion points: Processes external issue details and source code via exploration tools (SKILL.md).
  • Boundary markers: Absent; there are no specific delimiters to separate user data from instructions.
  • Capability inventory: Limited to the use of codebase-exploration and research_codebase for information gathering.
  • Sanitization: No explicit sanitization or instruction-filtering is applied to the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 06:29 PM
Security Audit — agent-trust-hub — work-breakdown