Social Media Reporter
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and YAML metadata. It does not include any Python scripts, Node.js packages, or shell commands.- [DATA_EXFILTRATION] (SAFE): No network-reaching utilities (curl, wget) or sensitive local file system paths (~/.ssh, ~/.aws) are present in the documentation or metadata.- [INDIRECT_PROMPT_INJECTION] (LOW): Although the skill is intended to process external social media data, it lacks the necessary capabilities (such as file-writing or subprocess execution) to be exploited via injected instructions. The risk is confined to the quality of the generated natural language report.
Audit Metadata