palantir-local-dev-loop

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSPRIVILEGE_ESCALATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing local configuration and test data files.
  • Ingestion points: Processes configuration from .env and data from tests/sample_data/ (SKILL.md).
  • Boundary markers: Does not specify markers to delimit data from instructions in input files.
  • Capability inventory: Executes commands via pip, python, and pytest for environment setup and testing (SKILL.md).
  • Sanitization: No data validation or sanitization is specified for the input sources.
  • [EXTERNAL_DOWNLOADS]: The instructions include steps to install standard dependencies like foundry-platform-sdk, pyspark, and pytest via pip. These are recognized packages from established registries for the skill's purpose.
  • [PRIVILEGE_ESCALATION]: Documentation regarding error handling suggests installing the JDK via apt install, which is a standard procedure for satisfying the system requirements of PySpark.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 09:36 PM
Security Audit — agent-trust-hub — palantir-local-dev-loop