skill-creator
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides procedural guidance and documentation for a developer workflow. It does not contain executable code itself, but rather references the structure of a skill ecosystem.
- [COMMAND_EXECUTION]: The documentation mentions the use of local scripts such as
scripts/init_skill.pyandscripts/package_skill.py. These are presented as standard development tools for initialization and validation within the vendor's (plastic-labs) workflow. - [INDIRECT_PROMPT_INJECTION]: As a meta-skill designed to create other skills, it describes patterns for ingesting data into an agent's context (e.g., through
references/andassets/). While this represents a data ingestion surface, the skill provides architectural guidelines to manage this securely and efficiently. - [METADATA_POISONING]: The skill's metadata (name and description) accurately reflects its purpose as a development aid for skill creation.
Audit Metadata