presentations
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents such as briefs and source materials to generate presentation outlines and stories.
- Ingestion points: The skill reads external "briefs and relevant sources" (SKILL.md) to inform content creation.
- Boundary markers: No explicit delimiters are defined within this specific skill file for isolating external content.
- Capability inventory: The skill itself does not possess direct file-write or network capabilities; it delegates slide creation and data handling to a separate artifact skill (
$orbit:slides-artifact). - Sanitization: The skill includes a specific safety instruction to check user access and follow confirmation policies before incorporating sensitive data into collaborative decks.
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts, binaries, or configuration files that could hide malicious logic.
Audit Metadata