kanban

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-controlled data such as task titles and descriptions which are intended for use with system tools like Bash and Write.\n
  • Ingestion points: Kanban card templates and bash command examples (e.g., /kanban-add) located in SKILL.md where user-provided input is expected.\n
  • Boundary markers: The skill does not define specific delimiters or instructions to differentiate between instructions and data in processed cards.\n
  • Capability inventory: The skill is permitted to use Bash, Read, Write, Edit, Glob, and Grep tools as specified in the frontmatter of SKILL.md.\n
  • Sanitization: No sanitization, validation, or escaping of external content is specified before interpolation into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 03:33 PM
Security Audit — agent-trust-hub — kanban