intent-to-3d-brief-writer
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural-language input (intent) and incorporates it into a structured brief consumed by downstream planning skills.
- Ingestion points: External data enters the agent context via the
raw_user_goal_and_contextinput defined incontract.jsonand is processed according to the operating procedure inSKILL.md. - Capability inventory: The skill is rated as Capability Tier L0.
SKILL.mdexplicitly states the skill does not run Blender, install software, or perform network operations. - Boundary markers: While the skill uses a structured 8-slot markdown template (
references/eight-slot-template.md), it does not mandate delimiters or boundary instructions when interpolating the user's intent into those slots. - Sanitization: There are no instructions to sanitize or validate the content of the user's intent before it is used to populate the brief.
Audit Metadata