semantic-spacetime

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's test suite (tests/test_semantic_spacetime.py) uses the subprocess module to run the local Python script (scripts/semantic-spacetime.py). This is a standard testing practice for CLI tools to verify exit codes and output behavior in a controlled environment and does not pose a threat to the execution environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data in YAML and JSON formats. This presents a potential attack surface for indirect prompt injection if the processed data contains malicious instructions. However, the risk is mitigated by the use of a custom RestrictedYamlParser that explicitly blocks dangerous YAML features like anchors and aliases, alongside a strict schema validator (sst-model-v1) that ensures only expected fields are processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:57 PM
Security Audit — agent-trust-hub — semantic-spacetime