ignav
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
curlcommands via the Bash tool to perform API requests for flight searches, airport lookups, and booking link generation.\n- [DATA_EXFILTRATION]: The skill performs network operations toignav.com, which is not on the predefined whitelist of domains for network traffic.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external API, creating a surface for potential instructions to be injected into the agent's context through flight information.\n - Ingestion points: Data is retrieved from
https://ignav.com/api/fares/one-way,https://ignav.com/api/fares/round-trip, andhttps://ignav.com/api/airports.\n - Boundary markers: No delimiters or safety instructions are present to ensure the agent ignores potentially malicious content within the API response.\n
- Capability inventory: The skill utilizes
Bash(curl *)for network-based data retrieval.\n - Sanitization: The instructions do not describe any sanitization or validation logic for the data received from the Ignav API before it is rendered into markdown tables for the user.
Audit Metadata