gpt-slide-generate
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from
DESIGN.mdandslide_prompts.jsonto generate slides, which constitutes an indirect prompt injection surface. - Ingestion points: External data enters the agent context from
DESIGN.mdandslide_prompts.jsonin the current workspace. - Boundary markers: No delimiters or instructions are provided to separate the ingested data from the agent's core instructions.
- Capability inventory: The skill has access to file reading and writing within the workspace and uses Codex image generation tools.
- Sanitization: No validation, escaping, or filtering of the content within the input files is performed.
Audit Metadata