pitch-deck
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands like 'soffice' and 'pdftoppm' to perform visual validation of generated documents. While these are legitimate tools for the task, they interact with user-controlled filenames and data.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external files. 1. Ingestion points: Phase 1 of SKILL.md identifies source materials like Excel, CSV, and PDF reports. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when reading source data. 3. Capability inventory: The skill uses subprocess calls to 'soffice' and 'pdftoppm' for file conversion (Phase 4 of SKILL.md). 4. Sanitization: The skill focuses on structural validation but lacks explicit sanitization of data contents.
Audit Metadata