tailor-resume

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill accepts a --jd-url= input (SKILL.md Inputs) and its Procedure §2 explicitly fetches/parses and analyzes the JD to extract must-haves/keywords and drive resume rewriting, meaning arbitrary public job postings could be ingested and influence agent decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill accepts a --jd-url parameter and fetches/parses that external URL at runtime to drive the resume-tailoring logic, so any arbitrary URL supplied via --jd-url is a runtime external dependency that directly controls the agent's prompts/instructions.