job-fit-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests job analysis files that may contain data from untrusted job descriptions, creating a surface for indirect prompt injection where hidden instructions could influence the agent's analysis.
- Ingestion points: Reads local files at
~/career-applications/[job-slug]/01-job-analysis.mdwhich contain external job requirements. - Boundary markers: The instructions do not specify explicit delimiters or 'ignore' directives for the data being analyzed.
- Capability inventory: The skill has the ability to read and write files in user directories and interact via the AskUserQuestion tool.
- Sanitization: No specific data validation or sanitization process is described for the processed text.
- [SAFE]: The skill operates on local career documents and uses standard interaction tools for career coaching. No network exfiltration, persistence mechanisms, or obfuscated patterns were detected in the instructions or workflow.
Audit Metadata