continue-claude-code-work
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session history and project-level configuration files that could contain malicious instructions.
- Ingestion points:
daymade-claude-code:read-claude-code-historytool output (SKILL.md),AGENTS.md,CLAUDE.md, and files within the working tree. - Boundary markers: The skill does not define explicit delimiters to separate instructions from processed data.
- Capability inventory: The agent is instructed to take direct actions (SKILL.md), which may include file modifications, command execution, and tool usage within the project scope.
- Sanitization: No explicit sanitization or validation of the history or project configuration content is defined.
Audit Metadata