resume-tailoring
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to process untrusted job descriptions and external web content. * Ingestion points: Untrusted data enters the agent context through user-provided job descriptions (text or URLs) and WebSearch/WebFetch results in SKILL.md and research-prompts.md. * Boundary markers: Absent; the prompt templates used for research and synthesis do not include explicit instructions or delimiters to isolate untrusted input from the agent's logic. * Capability inventory: The skill has the ability to read and write files, perform network searches, and generate documents via standard tools in SKILL.md. * Sanitization: Absent; no specific sanitization or validation of the input job description is observed before it is included in the processing pipeline.
Audit Metadata