explain-spsq

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local validation commands (synapseq -test or go run ./cmd/synapseq -test) to analyze sequence files. These commands are strictly for testing purposes, explicitly forbid audio rendering, and use local project paths from the same authoring foundation.
  • [DATA_EXPOSURE]: The skill accesses project-specific documentation and reference files (e.g., docs/SYNTAX.md, references/spsq-language.md) to ensure explanations remain accurate and grounded in the current language specification.
  • [PROMPT_INJECTION]: By processing user-supplied .spsq and .spsc files, the skill has a surface for indirect prompt injection. However, it contains explicit instructions to remain read-only and never modify or create project artifacts based on the input, which mitigates the risk of state-changing attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:41 PM
Security Audit — agent-trust-hub — explain-spsq