fact-checker
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- Data Exposure & Exfiltration (LOW): The skill accesses the local file system to read a document for review and checks for a specific configuration file at
~/.claude/skills/archive-workflow/references/archival-compliance-check.md. While these are functional requirements, they involve home-directory file access. - Data Exposure & Exfiltration (LOW): The skill performs network operations to resolve DOIs and verify source accessibility. This is consistent with its primary purpose of fact-checking.
- Indirect Prompt Injection (LOW): The skill possesses a vulnerability surface for indirect instructions embedded in the documents it processes.
- Ingestion points: Document files passed via path (e.g.,
path/to/document.md). - Boundary markers: None identified in the workflow instructions to separate document content from agent instructions.
- Capability inventory: File read operations, network requests for DOI verification, and report generation.
- Sanitization: No explicit sanitization or validation of the document content is described prior to analysis.
Audit Metadata