linkedin-profile-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the user to provide their 'current profile' text for optimization. This ingestion of untrusted external data creates a surface for indirect prompt injection if the profile contains hidden instructions intended to manipulate the agent. However, the risk is negligible as the skill lacks access to sensitive capabilities or network tools.\n
- Ingestion points: User-provided text in 'Step 1: Gather Information'.\n
- Boundary markers: None present.\n
- Capability inventory: Restricted to text generation and strategic advice; no command execution or network access.\n
- Sanitization: No input validation is implemented for the profile data.
Audit Metadata