palantir-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for fetching data from external Palantir Foundry resources, which could potentially contain malicious instructions intended to influence the agent.
- Ingestion points: Data is ingested via client.ontologies.OntologyObject.list and client.datasets.Dataset.read methods in the code examples.
- Boundary markers: There are no instructions or special characters defined to isolate the external data from the agent's core instructions.
- Capability inventory: The skill is granted tool permissions for Read, Write, Edit, and Bash, which could be exploited if an injection occurred.
- Sanitization: The provided Python and TypeScript examples do not demonstrate any validation or sanitization of the retrieved object properties or dataset contents before processing.
Audit Metadata