creative-plan
Warn
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill performs dynamic path computation for file system access at runtime.
- It calculates
PLUGIN_ROOTby performing string manipulation on theBase directoryenvironment variable. - It constructs
DOMAIN_DIRusing adomainvariable extracted from an untrusted project file (.creative/config.yaml). - The agent then executes
Readoperations on files within these computed paths (e.g.,$DOMAIN_DIR/domain.yaml,$DOMAIN_DIR/plan-guide.md). This logic lacks validation to ensure the resulting paths remain within intended directory boundaries. - [INDIRECT_PROMPT_INJECTION]: The skill's primary planning logic and quality control standards are ingested from external, potentially user-controlled files.
- Ingestion points: The skill reads
domain.yamlandplan-guide.mdfrom the project directory to define its planning layers, iteration logic, and output formats. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands when the agent processes the contents of these guide files.
- Capability inventory: The skill utilizes
Read,Write,Edit, andAskUserQuestiontools, allowing the ingested instructions to potentially influence file system modifications and user interactions. - Sanitization: The instructions do not specify any validation, escaping, or filtering for the content loaded from the domain configuration or planning guides.
Audit Metadata