job-description-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and templates for text analysis. It does not invoke any external scripts, binaries, or tools that could compromise the host system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external job descriptions provided by users. While this presents a surface for indirect prompt injection (e.g., a malicious job posting containing instructions to bias the match score), the skill has no dangerous capabilities such as file system writes, network exfiltration, or shell execution to exploit. The risk is limited to the accuracy of the generated report.
- Ingestion points: Processes job descriptions provided by the user in
SKILL.mdinstructions. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the input text.
- Capability inventory: The skill is restricted to text generation and logical analysis; it lacks network, file-write, or subprocess capabilities.
- Sanitization: No input validation or sanitization is implemented for the job description text.
Audit Metadata