discover-plugins
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied task descriptions or search queries to generate personalized plugin recommendations, creating a potential surface for indirect prompt injection.\n
- Ingestion points: User task descriptions provided to tools like
mcp__claude-flow__guidance_recommend.\n - Boundary markers: The skill does not define clear delimiters or 'ignore' instructions for user-provided data.\n
- Capability inventory: The skill has access to
Bashand multiple data retrieval MCP tools.\n - Sanitization: No evidence of input validation or sanitization before interpolation into prompts.\n- [COMMAND_EXECUTION]: Utilizes the
Bashtool to perform local directory listing (ls plugins/). This is a benign use of shell commands for discovering currently installed components.\n- [EXTERNAL_DOWNLOADS]: Provides instructions to download and install additional components from the vendor's repository (ruvnet/ruflo) via platform-specific/plugin installcommands. This functionality is consistent with the skill's purpose as an ecosystem discovery tool.
Audit Metadata