geo-content
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and evaluation criteria. It contains no scripts, binaries, or other executable files.
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by instructing the agent to fetch and process external web content. (1) Ingestion point: The skill fetches target URLs for analysis. (2) Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided. (3) Capability inventory: The agent's capabilities include reading web content and generating a markdown report. (4) Sanitization: No specific sanitization methods for the ingested content are described. This surface is inherent to the skill's core purpose of auditing web content.
- [SAFE]: No patterns of data exfiltration, credential harvesting, or unauthorized command execution were detected.
Audit Metadata