Skills
skills/orcaqubits/agentic-commerce-claude-plugins/webmcp-user-interaction/Gen Agent Trust Hub

webmcp-user-interaction

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches specifications from webmachinelearning.github.io, which is a recognized community resource for Web Machine Learning standards.
  • [COMMAND_EXECUTION]: The skill manifest includes the Bash tool, allowing for shell command execution.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection. Ingestion points: WebSearch and WebFetch (SKILL.md). Boundary markers: None. Capability inventory: Bash, Write, and Edit (SKILL.md). Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 07:33 AM
Security Audit — agent-trust-hub — webmcp-user-interaction