developing-with-ai
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of Markdown documentation files (SKILL.md, INSTRUCTIONS.md, and several reference guides). There are no shell scripts, Python files, JavaScript files, or other executable assets provided within the skill package.
- [PROMPT_INJECTION]: While the skill provides templates for interacting with AI models, these are standard development prompts for tasks like code generation, refactoring, and debugging. No patterns were found that attempt to bypass AI safety guidelines, extract system prompts, or override agent constraints.
- [DATA_EXFILTRATION]: There are no network-capable commands (e.g., curl, wget, fetch) or logic designed to access sensitive local data. All examples provided in the documentation use placeholder values or well-known, safe service references.
- [COMMAND_EXECUTION]: The skill does not contain any instructions that would lead to the execution of arbitrary shell commands or the spawning of subprocesses on the host system.
- [EXTERNAL_DOWNLOADS]: The documentation mentions external resources such as the Model Context Protocol (MCP) registry, but no automatic downloads or remote script executions are performed by the skill itself.
Audit Metadata