moai-alfred-proactive-suggestions

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requests access to the Bash tool to perform automation tasks. According to Example 2 in 'examples.md', the skill can generate and apply batch refactor scripts based on detected patterns in the user's codebase.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the 'WebFetch' tool and the 'mcp__context7__get-library-docs' MCP tool to retrieve external documentation and productivity patterns (e.g., fetching from '/productivity/docs' as seen in the 'ProactiveSuggestionsArchitectOptimizer' class).
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted data (external codebase and documentation) to generate suggestions that the agent may act upon.
  • Ingestion points: The skill reads local project files via 'Read'/'Glob' and fetches remote documentation via 'WebFetch' and 'Context7' MCP tools.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions for the processed content are present in the provided implementation snippets.
  • Capability inventory: The skill possesses powerful capabilities including 'Bash', 'Write', and 'Edit' tools, which could be leveraged if malicious instructions were successfully injected into the analyzed data.
  • Sanitization: The provided code does not demonstrate sanitization or validation of the external content before it is processed by the suggestion engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:06 AM