li-reply
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data (LinkedIn comments pasted by the user). This presents a surface for indirect prompt injection where malicious instructions could be embedded in a comment to influence the model's output. However, the risk is mitigated because the skill has no access to sensitive tools, cannot perform network or file operations, and includes an explicit requirement for the user to manually review and post the generated text, maintaining a human-in-the-loop safety boundary.
Audit Metadata