search
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and synthesize untrusted data from the internet.
- Ingestion points: The search workflow in SKILL.md uses
WebSearch,WebFetch, and multiple MCP research tools (Perplexity, Tavily, Exa, Context7, DeepWiki) to collect external information. - Boundary markers: The instructions provide formatting templates for the final answer but lack specific delimiters or "ignore instructions" directives to prevent the agent from accidentally obeying commands embedded in retrieved search results.
- Capability inventory: The skill is primarily research-oriented, but the compatibility sections for Codex and Cursor note that the agent may resolve primitives to powerful tools like
Bash,Write, andEdit. - Sanitization: No sanitization, filtering, or validation logic is specified for the data retrieved from external sources before it is processed by the agent.
Audit Metadata