job-description-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the ingestion of untrusted job description data.
- Ingestion points: The skill accepts untrusted data from pasted text, uploaded PDF/Word documents, and external URLs via the WebFetch tool as described in Phase 1 (Document Intake).
- Boundary markers: Absent. The skill instructions do not specify the use of delimiters or 'ignore' instructions to separate the untrusted input data from the agent's core instructions.
- Capability inventory: The skill has the capability to write Markdown and JSON files to the '~/career-applications/' directory and perform network read operations via the WebFetch tool.
- Sanitization: Absent. The extracted text from the job posting is processed directly and interpolated into the output analysis without explicit sanitization or escaping of potentially malicious content.
Audit Metadata