flovia
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Content retrieved from web searches (
flovia_exa) and specific page reads (flovia_firecrawl) is added to the model's context.\n - Boundary markers: The skill does not use specific delimiters or instructions to prevent the model from following commands found within the retrieved content.\n
- Capability inventory: The agent can call multiple MCP tools and execute the
./notifyscript.\n - Sanitization: No sanitization or filtering of external web content is specified before processing.\n- [COMMAND_EXECUTION]: The skill executes the local
./notifyscript to deliver results to the operator.
Audit Metadata