makepad-platform
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs imperative language including 'CRITICAL', 'IMPORTANT', and 'MUST' to guide the agent's internal workflow and prioritize documentation checks.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest content from local reference files, specifically './references/platform-support.md'. Ingestion points: local markdown file path. Boundary markers: None provided in instructions. Capability inventory: No risky tools or operations such as network requests, file writing, or subprocess execution are present in the skill's defined behavior. Sanitization: No specific input sanitization is implemented for the ingested reference data.
Audit Metadata