doc-kami-parchment
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate design artifacts, which presents a surface for indirect prompt injection.\n- Ingestion points: The user's message is treated as a brief and passed to the tool 'prepare_open_design_brief' in SKILL.md.\n- Boundary markers: Absent; there are no delimiters or instructions to ignore potential commands embedded within the user-provided brief.\n- Capability inventory: The agent is instructed to use its own file-editing tools and tools like 'register_open_design_artifact' based on instructions derived from the brief (SKILL.md).\n- Sanitization: Absent; the instructions do not specify any validation, filtering, or sanitization of the user's content before tool invocation.\n- [NO_CODE]: The skill does not include any executable scripts, binaries, or external code dependencies, consisting solely of markdown instructions and configuration.
Audit Metadata