israeli-cv-builder
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted job descriptions provided by the user to tailor the CV and extract keywords. This constitutes a potential surface for indirect prompt injection.\n
- Ingestion points: The 'Target role / job description' input described in
SKILL.mdandSKILL_HE.md(Step 1).\n - Boundary markers: The skill does not instruct the agent to use delimiters or ignore embedded instructions within the job description input.\n
- Capability inventory: The skill includes a local Python script (
scripts/cv_keyword_extractor.py) for keyword analysis. The skill itself does not have tools for network access, file system modification, or system command execution.\n - Sanitization: No sanitization or safety filtering is performed on the user-provided job description before it is processed by the agent or the keyword extraction script.
Audit Metadata