skills/thelobbi/claude/web-research/Gen Agent Trust Hub

web-research

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted web sources via tools like Perplexity and Firecrawl. This creates a surface for indirect prompt injection, where instructions hidden in scraped content might attempt to manipulate the agent's behavior.
  • Ingestion points: mcp__firecrawl__firecrawl_scrape, mcp__firecrawl__firecrawl_search, mcp__perplexity__perplexity_ask, and mcp__plugin_context7_context7__query-docs (SKILL.md).
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded commands within the retrieved text.
  • Capability inventory: The skill utilizes grep and glob for local codebase inspection alongside the external research tools.
  • Sanitization: Absent. The skill does not specify any filtering or validation for external content before it is synthesized into recommendations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — web-research