resume
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection because it is designed to ingest and process untrusted external data.
- Ingestion points: According to
SKILL.md, the agent is tasked with importing and scanning user-provided documents, including resumes, job descriptions, and data from LinkedIn or portfolio URLs. - Boundary markers: The skill instructions do not specify the use of clear delimiters or explicit instructions for the agent to disregard potential commands embedded within the external text data.
- Capability inventory: The skill uses file-writing capabilities to save the final Markdown CV to the local workspace as mentioned in
SKILL.md. It does not request or use high-risk tools such as arbitrary shell execution or network exfiltration. - Sanitization: The instructions do not include specific requirements for the agent to sanitize or validate content extracted from external sources before it is processed.
Audit Metadata