taxue-career
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external, untrusted content such as user-provided resumes and job descriptions. This ingestion of external data constitutes a surface for indirect prompt injection, where a malicious document could contain instructions intended to override agent behavior.\n
- Ingestion points: User resumes, job descriptions (JDs), and career project stories processed in
references/resume-jd.mdandreferences/case-factory.md.\n - Capability inventory: The skill is limited to providing career advice and routing to internal search tools (e.g.,
taxue-job-search). It does not have capabilities for unauthorized file writes or network exfiltration.\n - Boundary markers: The skill does not define explicit delimiters to isolate untrusted user data from its core instructions.\n
- Sanitization: No sanitization or filtering of the input text is specified in the skill's logic.
Audit Metadata