gsd-health

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by processing content from the .planning/ directory while possessing extensive system capabilities. • Ingestion points: Reads data from the .planning/ directory (SKILL.md). • Boundary markers: No delimiters are used to separate ingested data from agent instructions. • Capability inventory: Access to Read, Bash, Write, and AskUserQuestion tools (SKILL.md). • Sanitization: No validation or sanitization of input directory content is specified.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute health check and repair workflows stored in the platform root (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:08 PM