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 processes user-supplied LinkedIn profile content to perform audits and rewrites. This ingestion of untrusted external content represents a surface for indirect prompt injection, where malicious instructions embedded in a profile could attempt to influence agent behavior.
- Ingestion points: The skill ingests profile data during the 'Profile Audit' workflow described in
SKILL.md. - Boundary markers: There are no specific delimiters or boundary markers defined in the instructions to isolate external profile data from the agent's primary instructions.
- Capability inventory: The skill is limited to text analysis and generation; it does not request capabilities such as network access, file system modifications, or shell command execution.
- Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the incoming profile content.
Audit Metadata