linkedin-profile-optimizer

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely instructional and does not contain any executable scripts, binaries, or command-line operations. It relies on the underlying LLM's natural language capabilities to perform profile audits and rewrites.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for processing untrusted data by asking users to paste their LinkedIn profile content. (1) Ingestion points: User input requested in 'Step 1 — Intake' (headline, about section, experience bullets). (2) Boundary markers: Absent; the skill does not use specific delimiters to isolate user-provided profile text from its own instructions. (3) Capability inventory: None detected. The skill does not use any tools for file system access, network communication, or shell execution. (4) Sanitization: Absent; the skill performs direct interpolation of user text into its processing logic.
  • [EXTERNAL_DOWNLOADS]: Includes a reference to the author's repository at github.com/BrianRWagner/ai-marketing-skills. This is a plain-text link to a vendor-owned resource and does not trigger automated downloads or execution of external code.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 05:19 PM