international-seo-hreflang-audit
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML content from external websites, creating a surface for indirect prompt injection if the audited site contains malicious metadata.
- Ingestion points: HTML content and headers are fetched from external URLs via curl in references/checks.md.
- Boundary markers: Absent; the skill lacks delimiters or explicit instructions to treat the ingested data as untrusted.
- Capability inventory: The skill uses curl, grep, and python3 subprocesses in references/checks.md to parse data and generate reproduction commands.
- Sanitization: Absent; the Python scripts in references/checks.md extract attributes directly using BeautifulSoup without validation or escaping.
- [COMMAND_EXECUTION]: The audit workflow relies on the execution of shell commands. Evidence: references/checks.md includes bash snippets for extracting tags, checking headers, and verifying reciprocity using curl and python3.
- [EXTERNAL_DOWNLOADS]: The skill references a third-party Python package that is not part of the standard library. Evidence: The script in references/checks.md imports 'bs4' (BeautifulSoup), which must be installed in the environment.
Audit Metadata