The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to extract and analyze text from external PDF files, which are untrusted inputs. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in a document could override agent behavior. * Ingestion points: Processing of PDF files and text extraction (SKILL.md). * Boundary markers: Absent; the instructions do not recommend using delimiters or warnings to ignore commands within the document. * Capability inventory: The skill does not define custom executable code or network access, relying on the platform's default tools. * Sanitization: No sanitization, validation, or filtering of the extracted text content is specified in the instructions.
[NO_CODE]: The skill consists entirely of markdown documentation and instructions with no accompanying scripts or executable code, which limits the potential for direct system compromise.

pdf-processing