table-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
camelot-pyandpandasPython packages, as well as system dependencies likeghostscriptandtcl-tkvia package managers (pip,brew,apt-get). These are standard requirements for the library's stated functionality. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse external PDF documents, which creates a potential surface for indirect prompt injection if an adversary embeds malicious instructions within a PDF to influence the agent's behavior during or after extraction.
- Ingestion points: Processes external PDF files via
camelot.read_pdfinSKILL.md. - Boundary markers: No explicit markers are defined to delimit or sanitize the extracted content from the rest of the prompt.
- Capability inventory: The skill has file-writing capabilities through methods such as
to_csv,to_excel,to_json,to_html, andfig.savefig(as documented inSKILL.md). - Sanitization: The instructions do not specify any sanitization, validation, or filtering of the extracted content before it is processed or exported.
Audit Metadata