compdf-toolkit
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from various external file formats (PDF, HTML, Office, etc.), creating a surface for potential prompt injection attacks embedded within those documents.\n
- Ingestion points: The workflow involves reading and processing user-supplied files such as PDFs and images for conversion and OCR (
SKILL.md).\n - Boundary markers: The instructions do not provide explicit delimiters or guidance for the agent to distinguish between its instructions and the content within the processed documents.\n
- Capability inventory: The skill allows the agent to perform network requests to the ComPDF API, including file uploads and metadata extraction (
references/endpoint-index.md).\n - Sanitization: No sanitization or filtering logic is specified for the content extracted from processed documents before it is used in subsequent steps or API calls.
Audit Metadata