jd-match
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests resumes and job descriptions from external, untrusted sources which could contain malicious instructions designed to influence the agent's analysis or output.\n
- Ingestion points: The skill reads job description text, fetches content from external URLs, and processes resume files in various formats (PDF, DOCX, LaTeX, MD, text) as described in Section 0.\n
- Boundary markers: There are no explicit instructions or delimiters defined to separate the untrusted document content from the agent's operational instructions, nor is the agent told to ignore instructions embedded within the JD or resume.\n
- Capability inventory: The agent has the capability to read local files, call other internal tools (
cracked-profile,company-intel), and write analysis files to the$CRACKED_DIR/jd/directory (Section 4).\n - Sanitization: The instructions do not specify any validation or sanitization steps for the data extracted from the external documents before it is used in calculations or file writing.
Audit Metadata