geo-technical
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill consists of a structured set of instructions for auditing website technical health. It does not include any malicious code, external dependencies, or persistence mechanisms.
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it is designed to ingest and process untrusted content from external URLs (HTML and headers) as described in SKILL.md. An attacker could attempt to influence the agent by embedding malicious instructions within a website's content. Boundary markers: While explicit delimiters for external content are not mandated, the skill's specific audit categories, detailed scoring rubrics, and the required 'GEO-TECHNICAL-AUDIT.md' output format act as functional constraints on the agent's behavior. Ingestion points: Target URLs fetched via curl or WebFetch. Capability inventory: The skill uses Bash for performance checks and Write to generate the audit report. Sanitization: No explicit sanitization or filtering of external content is described.
- [COMMAND_EXECUTION]: The skill provides instructions for using
curlto measure performance metrics such as Time to First Byte (TTFB). These commands are used for their intended purpose of technical analysis and do not involve the execution of untrusted scripts or privilege escalation.
Audit Metadata