Skills
Navigate
skills/athola/claude-night-market/night-market-config-catalog/Gen Agent Trust Hub

night-market-config-catalog

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides diagnostic shell commands—including jq, rg, ls, and head—for the agent to verify the state and content of local configuration files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository configuration files, creating a vulnerability surface.
  • Ingestion points: Local config files like .claude/quality_gates.json, .claude/context_governance.json, and pyproject.toml.
  • Boundary markers: Absent; no delimiters are used to separate configuration content from instructions.
  • Capability inventory: Diagnostic shell tools (jq, rg, ls, head).
  • Sanitization: Absent; configuration data is processed without escaping or validation.
  • [EXTERNAL_DOWNLOADS]: The skill references external tools including the markitdown-mcp server (run via uvx) and pinned versions for pre-commit hooks and bandit.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:06 AM
Security Audit — agent-trust-hub — night-market-config-catalog