sharemd
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a setup command (
claude mcp add) for the user to manually configure the MCP tool connection with their API key. - [DATA_EXFILTRATION]: Transmits conversation content and local file data to the external service at
sharemd.dev. This is the core functionality of the skill and uses the vendor's service domain. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from the conversation and local files for transmission. * Ingestion points: Chat history and local file system paths (SKILL.md). * Boundary markers: Not specified. * Capability inventory: Tool
mcp__sharemd__share-markdownperforms network writes to an external service. * Sanitization: No specific filtering or escaping is described for the content before sharing.
Audit Metadata