clinic-website-ai-search
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
curlto fetch website headers (curl -sIL) and raw HTML (curl -sL) to verify redirects, status codes, and the presence of SEO elements like JSON-LD and meta tags. - [EXTERNAL_DOWNLOADS]: The skill's primary function involves downloading content from external URLs provided by the user to perform audits.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from third-party websites, creating a vulnerability surface where malicious instructions on a scanned site could attempt to influence the agent.
- Ingestion points: External website content and headers fetched via
curl(SKILL.md). - Boundary markers: Absent; the agent is not instructed to use specific delimiters or ignore instructions when processing the fetched content.
- Capability inventory: Uses shell commands (
curl) and generates analysis reports based on external data. - Sanitization: Absent; the agent reads raw HTML and headers directly to extract data.
Audit Metadata