skills/neg0diay/skills/loop-me/Gen Agent Trust Hub

loop-me

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill instructions are focused on guiding the user through a requirement-gathering process ('grilling') to define automation workflows.
  • [SAFE]: The skill interacts with local workspace files (NOTES.md and workflows/*.md) to store and retrieve workflow specifications. This is consistent with its described functionality and does not involve external data transmission or unsafe command execution.
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected.
  • Ingestion points: Reads from NOTES.md (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Creates, edits, and deletes files in workflows/*.md and NOTES.md (SKILL.md).
  • Sanitization: Absent.
  • Analysis: The skill reads user context from a local file to inform its questioning process. While this represents a data ingestion surface, the risk is mitigated by the restricted scope of its actions (local file management for documentation) and the absence of network or system-level capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:37 PM
Security Audit — agent-trust-hub — loop-me