career-ops

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process job descriptions (JDs) and URLs from external, untrusted sources to automate career-related tasks. This creates a surface where an attacker could embed malicious instructions within a job posting to influence the agent's behavior during evaluation, CV tailoring, or application drafting.
  • Ingestion points: The skill uses user-provided JD text and URLs as the primary input for the auto-pipeline and scan modes.
  • Boundary markers: The routing instructions do not specify the use of delimiters or boundary markers to isolate untrusted JD content from the agent's core instructions.
  • Capability inventory: The skill facilitates a wide range of sensitive tasks including generating PDFs, tailoring CVs, drafting emails, and tracking application statuses.
  • Sanitization: No explicit sanitization, filtering, or validation logic is defined in the router for the external content it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 07:26 PM
Security Audit — agent-trust-hub — career-ops