meta-competitive-intel
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The analysis did not reveal any malicious patterns, exfiltration attempts, or unauthorized access. The skill is authored by the vendor and uses expected bundled capabilities.
- [EXTERNAL_DOWNLOADS]: The skill orchestrates web searches via a bundled search engine tool to gather competitive intelligence. This activity is restricted to its primary research purpose.
- [COMMAND_EXECUTION]: The skill uses platform capabilities to write research results to Excel (.xlsx) and Word (.docx) files within the system's temporary directory for user download. This is standard reporting functionality.
- [PROMPT_INJECTION]: The skill processes untrusted input from users and external search results, presenting a surface for indirect prompt injection.
- Ingestion points: External data enters the context via the initial user message and subsequent web search results used in summarization steps.
- Boundary markers: The skill employs clear headers (e.g., 'User request:', 'Search results:') and structured output contracts to delimit data from instructions.
- Capability inventory: The skill has the ability to write to the file system and perform network searches using designated tools.
- Sanitization: Input data is sanitized using XML escaping and character truncation to reduce the risk of malicious payload execution.
Audit Metadata