deep-dive
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it fetches and processes untrusted external content from the web via the
WebFetchandWebSearchtools. This is inherent to the skill's primary function of web-based research. - Ingestion points: Data enters the agent's context through content fetched by sub-agents using the
WebFetchtool in Phase 2. - Boundary markers: The instructions do not define explicit delimiters (like XML tags) or specific directives for sub-agents to ignore instructions contained within the fetched web content.
- Capability inventory: The skill utilizes
Bash,Read,Write,WebSearch,WebFetch,Agent, andAskUserQuestiontools. - Sanitization: No explicit sanitization or filtering of the fetched content is performed prior to analysis and synthesis.
Audit Metadata