storyboard-to-slides
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from a CSV file.
- Ingestion points: The script reads content from 'storyboard.csv', specifically the 'title', 'bullet_points', and 'speaker_notes' columns, in 'SKILL.md'.
- Boundary markers: There are no explicit boundary markers or instructions to ignore potential commands embedded within the CSV data.
- Capability inventory: The skill is limited to file system access for reading the storyboard and images and saving the resulting .pptx file. It does not possess network access or dynamic execution capabilities (like eval or subprocess).
- Sanitization: No sanitization, escaping, or validation is performed on the text extracted from the CSV before it is inserted into the PowerPoint text frames.
Audit Metadata