skills/tmdgusya/lora/lore-setup/Gen Agent Trust Hub

lore-setup

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's behavior is consistent with its stated purpose of configuring project settings. No malicious code, obfuscation, or unauthorized data access was detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill modifies agent configuration files (AGENTS.md, CLAUDE.md) to define future behavior regarding commit message formatting. This creates an instruction persistence surface.\n
  • Ingestion points: Agent configuration files (AGENTS.md, CLAUDE.md, ~/.claude/CLAUDE.md, ~/.agents/AGENTS.md).\n
  • Boundary markers: Uses markdown headers (e.g., '## Commit Messages: Lore Format').\n
  • Capability inventory: The skill performs file append operations to modify environment settings.\n
  • Sanitization: The skill writes a static, predefined instruction block.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:36 AM
Security Audit — agent-trust-hub — lore-setup