linkedin-optimizer

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data such as resumes and LinkedIn profiles, which could potentially contain malicious instructions meant to influence the agent's behavior.
  • Ingestion points: Reads from my-documents/resume.md, my-documents/cv.md, my-documents/story-bank.md, and user-provided LinkedIn PDF files or text pastes.
  • Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore embedded commands within the ingested data.
  • Capability inventory: The skill has capabilities to read/write files and execute local scripts.
  • Sanitization: There is no mention of filtering or sanitizing the input data before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script to determine the user's profile strength.
  • Execution method: Executes node "{job_hunt_skills_root}/scripts/profile-strength.mjs". This is a routine operation for calculating profile metrics within the skill's intended context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 02:29 PM
Security Audit — agent-trust-hub — linkedin-optimizer