resume-tailor-analyze
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted job description and resume files (e.g., data/resume.md, job.json) without explicit boundary markers or sanitization, creating a potential surface for indirect prompt injection.
- Ingestion points: data/resume.md, data/resume.star.md, data/profile.md, data/experience-bank.md, and job.json.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' commands for input content.
- Capability inventory: Writing matching analysis to markdown and JSON files. No shell command execution or network capabilities are explicitly invoked in the provided logic.
- Sanitization: Absent; no filtering or validation of input text is defined.
Audit Metadata