resume-writer
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (career notes and interview answers) which could potentially contain malicious instructions designed to manipulate the agent's output or tool usage.
- Ingestion points: User-provided 'raw career notes' and answers to elicitation questions in Step 1 as described in SKILL.md.
- Boundary markers: The instructions do not employ delimiters or specific warnings to ignore instructions embedded within the user-provided data.
- Capability inventory: The skill uses the 'docx' tool to generate files and has the capability to pass content to an external 'Resume Reviewer' skill.
- Sanitization: There is no evidence of input validation, escaping, or sanitization before user-provided content is processed for document generation.
Audit Metadata