marp-deck-planner
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content from an external file without adequate isolation.\n
- Ingestion points: The skill reads input from
definition/deck-definition.mdas part of its primary workflow.\n - Boundary markers: No delimiters or instructions to ignore embedded commands are present in the prompt structure.\n
- Capability inventory: The skill only generates a Markdown file (
planning/deck-plan.md). It lacks capabilities for network access, shell execution, or system modification.\n - Sanitization: No input sanitization is performed on the content of the definition file.\n- [NO_CODE]: The skill is purely instruction-based and does not contain any scripts, compiled binaries, or external software dependencies.
Audit Metadata