linkedin-audit

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard file system tools (Read, Write, Edit, Bash) to manage profile data and generate audit reports. These operations are consistent with the skill's primary purpose of profile optimization.
  • [DATA_EXPOSURE]: The skill accesses sensitive local files containing career plans and work history (career-plan.yaml, experience-library.yaml). This access is necessary for the audit functionality and the data remains within the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, user-provided data from Job Description (JD) files located in vault/uploads/jds/. While this introduces a potential surface for indirect prompt injection if a JD contains malicious instructions, the risk is minimized as the output is restricted to report generation and local logging.
  • Ingestion points: Files in vault/uploads/jds/.
  • Boundary markers: None present.
  • Capability inventory: Read, Write, Edit, Bash, and blackboard communication tools.
  • Sanitization: No explicit sanitization of JD content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 05:35 AM
Security Audit — agent-trust-hub — linkedin-audit