octolens
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted third-party content from social listening feeds, which is a potential injection surface. However, the skill explicitly includes guardrails instructing the agent to treat mention text as data only and never as instructions, mitigating this risk.
- [SAFE]: No malicious patterns such as remote code execution, credential harvesting, or obfuscation were detected in the skill instructions.
Audit Metadata