fondo-deploy-integration
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an integration that consumes data from an external API, creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested via the
/healthendpoint defined inSKILL.md, which fetches status fromhttps://api.tryfondo.com/v1/compliance/status. - Boundary markers: There are no explicit instructions or delimiters defined to isolate or ignore potentially malicious instructions embedded in the API responses.
- Capability inventory: The skill uses the
Bashtool to executedockerbuild, run, and stop commands, and manages environment variables. - Sanitization: The implementation includes basic error handling that returns error messages, but lacks robust validation or sanitization of the external API payload.
- [COMMAND_EXECUTION]: The skill provides automated shell commands for container lifecycle management.
- Evidence:
SKILL.mdincludesdocker build,docker run, anddocker stopcommands intended for deploying and updating the integration service.
Audit Metadata