ai-market-landscape
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to perform extensive web searches to gather data for competitive analysis. This creates a vulnerability surface where malicious instructions embedded in third-party websites could influence the agent's behavior during the analysis process.
- Ingestion points: External data enters the context via 10-15 web searches as specified in the 'Research-First Workflow' section of SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore potentially malicious content found during the research phase.
- Capability inventory: The skill is restricted to text generation and does not have scripts or tools that perform file system writes, network requests (beyond searching), or command execution.
- Sanitization: There are no explicit instructions for the agent to sanitize or filter the content retrieved from web searches before generating the analyst briefing.
Audit Metadata