glmv-pdf-to-ppt
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto download PDF files from remote URLs provided by the user (SKILL.md, Phase 1). - [COMMAND_EXECUTION]: The skill executes multiple local Python scripts to perform PDF conversion, image cropping, and slide generation (
pdf_to_images.py,crop.py,generate_slide.py). It also invokespip installto manage dependencies (SKILL.md). - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes untrusted data from PDF files which the agent is instructed to 'read' and 'absorb' (SKILL.md, Phase 2).
- Ingestion points: External PDF documents provided via local path or URL (SKILL.md).
- Boundary markers: No specific delimiters or instructions are provided to the agent to ignore potentially malicious commands embedded within the PDF content.
- Capability inventory: The skill possesses network access (via
curl), file system write capabilities, and the ability to execute shell commands and Python scripts. - Sanitization: There is no evidence of sanitization or filtering of the visual or textual content extracted from the PDF images before the agent processes them.
Audit Metadata