antislop-docs
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from documents such as docx, PDF, and Google Docs. \n
- Ingestion points: External document files and API-based document content (referenced in SKILL.md). \n
- Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the processed documents. \n
- Capability inventory: Text analysis and document structure modification; mentions integration with libraries like python-docx and docx-js. \n
- Sanitization: No sanitization or escaping mechanisms for external content are described. \n- [NO_CODE]: The skill consists entirely of markdown instructions and configuration parameters. It does not contain any executable scripts, shell commands, or active code blocks.
Audit Metadata