grace-status

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes content from project files, which constitutes a data ingestion surface. Maliciously crafted content in source files could potentially influence agent behavior during the scan.
  • Ingestion points: Source files and documentation referenced in SKILL.md.
  • Boundary markers: None specified.
  • Capability inventory: The skill suggests executing CLI commands like $grace-execute.
  • Sanitization: No sanitization of ingested file content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 01:16 PM