The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill serves as a documentation resource for using standard PDF processing libraries.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external PDF files through text and table extraction. This capability creates an attack surface for indirect prompt injection if an attacker embeds malicious instructions within a PDF processed by the agent. However, this is an inherent risk of document processing tools and is mitigated by the skill's inclusion of security best practices like metadata scrubbing and redaction verification.

document-pdf