social-media-bio-generator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (LOW): No security findings identified. The skill is entirely declarative and focuses on text generation based on provided patterns.
- DATA_EXPOSURE (INFO): The skill instructions include reading from
/context/voice-dna.json,/context/icp.json, and/context/business-profile.json. This is standard behavior for personalizing agent output and no data exfiltration vectors (network or write operations) are present. - INDIRECT_PROMPT_INJECTION (INFO): The skill processes external JSON data. While this is an ingestion surface, the skill has no dangerous capabilities (commands, network, or file writes) to exploit, limiting the risk to output bias or logic manipulation within the bio generation itself.
Audit Metadata