dev
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard development tools such as
rg(ripgrep) for code search andgitfor commit history and status. These operations are scoped to the project environment and used for context gathering during the 'Shared prep' and 'implement' phases. - [EXTERNAL_DOWNLOADS]: The skill integrates with Model Context Protocol (MCP) tools like
user-dash-apiandContext7to retrieve documentation. These are platform-level integrations for context retrieval rather than arbitrary remote code downloads from untrusted sources. - [PROMPT_INJECTION]: Functional constraints are present (e.g., refusing to answer product strategy questions or inventing APIs), which serve to maintain the agent's focus on implementation and accuracy rather than bypassing safety or behavioral guardrails. The skill processes project-specific files like
AGENTS.mdandCONTEXT.mdto guide its behavior, which is standard for development-oriented agents.
Audit Metadata