proofread-presentation
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected. The skill operates on local project files and uses standard development tools for presentation validation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from PRESENTASJON.md which presents a potential surface for indirect prompt injection. 1. Ingestion points: Processes user-provided PRESENTASJON.md, DISCOVERY.json, and PROJECT.json files. 2. Boundary markers: Does not explicitly define boundary markers or 'ignore' instructions for the ingested content. 3. Capability inventory: Executes shell commands including marp CLI and mktemp to generate slide images for review. 4. Sanitization: No explicit sanitization or filtering of the markdown content is described before it is rendered by Marp.
Audit Metadata