deep-knowledge-skill-creator
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
git submodule addto retrieve external documentation repositories for analysis. A provided example targets theMicrosoftDocsGitHub organization, which is a well-known and trusted source. - [COMMAND_EXECUTION]: Standard system commands including
git,cd,ls, andgrepare used to manage local repository files and analyze content structure during the multi-phase workflow. - [PROMPT_INJECTION]: The skill processes content from external repositories, which presents a surface for indirect prompt injection. However, this is inherent to its primary purpose of documentation analysis.
- Ingestion points: Documentation repositories added via git submodules.
- Boundary markers: Not explicitly defined in the sub-agent task prompts.
- Capability inventory: The workflow orchestrates agent teams to perform research and generate skill content.
- Sanitization: Not specified in the provided workflow.
Audit Metadata