cv-creator

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation points to a production-ready implementation hosted on the author's GitHub repository (github.com/erichowens/cv-creator). This is a vendor-managed resource.
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection vulnerability surface through its 'Quick Optimization' workflow, which processes external data.
  • Ingestion points: The skill uses the WebFetch tool to ingest job descriptions directly from external URLs provided by the user (described in references/interfaces-integration.md).
  • Boundary markers: No specific boundary markers or defensive instructions (e.g., delimiters or warnings to ignore embedded instructions) are documented for the ingestion of external job descriptions.
  • Capability inventory: The skill has access to several powerful tools, including Read, Write, Edit, WebFetch, and WebSearch (specified in SKILL.md).
  • Sanitization: There is no evidence of sanitization, filtering, or validation processes for the data fetched from remote job descriptions before it is integrated into the prompt for resume tailoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:02 PM