nika-debugging

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the Nika CLI tool via a specific Homebrew tap (supernovae-st/tap/nika). This resource is managed by the skill's author and is consistent with standard installation practices for the tool suite.
  • [COMMAND_EXECUTION]: The skill documents the use of various CLI subcommands such as nika run, nika trace, nika check, and nika doctor. These commands are used to execute, inspect, and audit the environment of Nika workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze trace data from previously executed runs, which represents an ingestion surface for potentially untrusted data.
  • Ingestion points: The skill reads hash-chained journals from the .nika/traces/ directory (SKILL.md).
  • Boundary markers: Security is managed via a permits: block which defines the authority and environment access for the workflow.
  • Capability inventory: The skill uses CLI tools to perform execution (nika run), forensic replay, and environment auditing (nika doctor).
  • Sanitization: The documentation emphasizes the use of nika trace verify to ensure the integrity of the trace journal, detecting any tampering through hash-chain verification before the data is trusted for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 08:26 PM