day2-supplement-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill automatically executes a command to synchronize its instructional content with the author's repository.
- Evidence: The start block in
SKILL.mdinvokesnpx skills add ai-native-camp/camp-1 --agent claude-code --yes. This is a vendor-owned resource used for updating the tutorial materials. - [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing and configuring various external tools and extensions.
- Evidence: The reference files (
block1-add-server.md,block3-popular-servers.md,block4-plugin-mcp.md) guide users to install MCP servers from official sources (Anthropic), well-known providers (Notion, Slack, Sentry, Linear, Upstash), and community repositories (obra/superpowers-marketplace). - [INDIRECT_PROMPT_INJECTION]: The skill processes user selections via interactive prompts to control the flow of the educational content and demonstrate tool installation.
- Ingestion points: User responses to
AskUserQuestionmenus and quiz interactions inSKILL.mdand all reference files. - Boundary markers: The skill implements a strict "STOP PROTOCOL" to ensure explanations and executions are separated from user feedback turns.
- Capability inventory: The skill utilizes subprocess execution for package management and tool configuration (
npx,claude mcp). - Sanitization: Not explicitly implemented in the skill instructions; the skill relies on predefined command structures for its tutorial steps.
Audit Metadata