taleb-perspective
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates a mandatory 'Agentic Protocol' in
SKILL.mdthat requires the agent to useWebSearchtools to research facts before responding. This creates a surface for indirect prompt injection.\n - Ingestion points: The agent is instructed to ingest data from arbitrary web results retrieved by the
WebSearchtool.\n - Boundary markers: Absent. The instructions do not provide delimiters or negative constraints to prevent the agent from following instructions hidden within the fetched web content.\n
- Capability inventory: The agent has the ability to execute web searches and perform complex persona-driven reasoning, which could be subverted by malicious external content.\n
- Sanitization: No explicit sanitization or validation of the external content is mandated in the skill instructions.
Audit Metadata