web-research

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web via the WebSearch tool, creating a surface for indirect prompt injection where malicious content on websites could attempt to influence agent behavior.\n
  • Ingestion points: Web search results (titles, URLs, snippets) are processed in Step 2 and Step 3 of the research protocol in SKILL.md.\n
  • Boundary markers: The skill explicitly requires cross-validation of all claims using at least two independent sources and mandates a confidence declaration (95/80/60/<60%).\n
  • Capability inventory: The agent is authorized to use WebSearch, write to the local file system (tmp/research/, docs/knowledge/, tmp/reports/), and spawn subagents via spawn_agent.\n
  • Sanitization: The protocol includes a mandatory triage step (Step 3) that classifies sources into tiers (1-4) and deduplicates content to ensure only high-signal information is used.\n- [DYNAMIC_EXECUTION]: The skill conditionally loads and executes additional instructions from local files based on user-provided flags.\n
  • Evidence: When the --chain=deep-dive flag is passed, the skill reads and follows procedures defined in references/research-chain.md and .claude/skills/source-deep-dive/SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:42 PM