skills/fradser/dotclaude/storm-engine/Gen Agent Trust Hub

storm-engine

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the shell utility mktemp -d to create temporary directories for storing research artifacts if a permanent path is not provided.
  • [EXTERNAL_DOWNLOADS]: The research process involves automated searching and fetching of content from web sources (via MCP or WebSearch) to populate research sources and information tables.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the web and user documents, presenting a surface for indirect prompt injection. Ingestion points: Web search results, fetched page snippets, and user-provided document directories (SKILL.md). Boundary markers: No specific security delimiters or 'ignore' instructions are provided for retrieved data. Capability inventory: The system performs file creation/writes and network operations (search/fetch) across all research phases (SKILL.md). Sanitization: While the skill provides logic to strip existing citations from snippets, no security-focused sanitization or filtering of external input is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 03:06 AM
Security Audit — agent-trust-hub — storm-engine