skills/tkersey/dotfiles/mesh/Gen Agent Trust Hub

mesh

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates a workflow where external CSV row content is interpolated into sub-agent instruction templates, which is a standard vector for indirect prompt injection.
  • Ingestion points: User-provided CSV data files ingested via the spawn_agents_on_csv function.
  • Boundary markers: The skill relies on {column} placeholders for data interpolation but lacks instructions for using delimiters to isolate data from instructions.
  • Capability inventory: Spawns sub-agents capable of executing a wide range of tasks based on instruction templates, including reading and writing files.
  • Sanitization: No data sanitization, escaping, or validation of the CSV content is implemented or recommended within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:35 AM