workspace-manager
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text defining a workflow for project management and narrative data isolation.
- [NO_CODE]: There are no executable scripts, shell commands, binary files, or external dependencies included in the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external project data (novels and bibles). However, it explicitly mandates isolation rules, namespaces, and manual overrides to prevent cross-novel leakage. As the skill lacks any execution capabilities or tools, the risk of instruction injection via these files is effectively mitigated.
- [DATA_EXFILTRATION]: The file paths referenced (e.g., workspace/PROJECT.md, NOVEL_BIBLE.md) are structural to the workspace and do not involve access to sensitive system credentials, user environment variables, or network communication.
Audit Metadata