linkedin-profile-optimizer
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill is designed to ingest and process LinkedIn Profile Links, CVs/Resumes (PDF, Text, or Hosted), and Portfolio Links from various platforms like GitHub and Behance (identified in 'Input Types' and 'Phase 0').
- Boundary markers: There are no specific instructions or delimiters used to isolate external content from the system instructions, nor are there warnings to the agent to ignore any embedded commands within the ingested data.
- Capability inventory: The agent uses browsing tools to fetch profile data and performs text generation/optimization based on that external input.
- Sanitization: The skill lacks mechanisms for sanitizing or validating external content before it is interpolated into the prompt context for analysis.
Audit Metadata