web-search
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it facilitates workflows that ingest untrusted content from the web and process it through LLMs without explicit sanitization.
- Ingestion points: External web content is fetched using the
tavily/extractandexa/extractapps via theinfshCLI tool. - Boundary markers: The workflow examples in
SKILL.mdinterpolate search and extraction results directly into LLM prompts using simple placeholders like<search-results>and<content>without using robust delimiters or defensive instructions. - Capability inventory: The skill is authorized to use the
infshcommand to execute search, extraction, and inference tasks. - Sanitization: There is no evidence of validation or sanitization of the retrieved web content before it is processed by downstream AI models.
Audit Metadata