swot-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted information from web searches and user-provided inputs to generate business analysis documents. This creates a surface where malicious instructions embedded in external web content could potentially influence the agent's behavior, analysis outcomes, or the content of the generated Word document.
- Ingestion points: External facts gathered via web search and company information provided by the user as described in the workflow (SKILL.md).
- Boundary markers: The instructions do not specify clear delimiters or warnings to ignore instructions embedded within the retrieved data.
- Capability inventory: The skill uses web search tools to gather facts and a Word document generation tool to output the final analysis.
- Sanitization: No explicit sanitization or validation of the retrieved external content is mentioned before it is processed and interpolated into the final output.
Audit Metadata