moai-alfred-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface.\n
  • Ingestion points: The CodeReviewTemplate and FeatureDevelopmentTemplate (examples.md) accept external inputs such as pr_url and feature_description. Furthermore, the Context7Integration (SKILL.md) retrieves search results from external MCP servers.\n
  • Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to treat external content as untrusted or to ignore embedded instructions.\n
  • Capability inventory: The skill is granted access to powerful tools including Bash, Write, Edit, and WebFetch. The WorkflowEngine executes tasks that could be influenced by malicious content within the ingested data.\n
  • Sanitization: No evidence of sanitization, filtering, or strict schema validation for the external content is present in the provided source code or configuration.\n- [EXTERNAL_DOWNLOADS]: The skill integrates with external services using established and trusted channels.\n
  • Trusted Integrations: Configuration references @anthropic-ai/mcp-server-github, which is maintained by a trusted organization.\n
  • Well-Known Services: The integration with @upstash/context7-mcp utilizes a well-known technology service. These external references are appropriate for the skill's enterprise automation purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:06 AM