cv-resume-builder
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to process user-provided career histories and external job descriptions to extract keywords and tailor content, as detailed in
SKILL.mdunder 'Tailoring Strategy' and 'ATS Optimization'. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external job description text as untrusted data or to ignore any embedded commands.
- Capability inventory: The skill is primarily focused on text analysis and markdown generation based on provided templates (e.g.,
assets/templates/academic-cv.md). It does not define any shell execution, network exfiltration, or file-writing tools. - Sanitization: The instructions do not include steps for the agent to sanitize or filter input from job postings before processing them.
Audit Metadata