seo-migration
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing untrusted data from external sources.\n
- Ingestion points: The skill crawls original site pages recursively (Step 1) and extracts JSON-LD and microdata (Step 4).\n
- Boundary markers: There are no explicit instructions or delimiters to tell the agent to ignore instructions that might be embedded in the crawled website content or metadata.\n
- Capability inventory: The agent performs network requests (crawling) and writes configuration files (next.config.ts, vercel.json) and validation reports (Step 2, Step 5, Step 6).\n
- Sanitization: No sanitization or validation logic is defined to clean the extracted external content before it is used to generate site configurations or reports.\n- [COMMAND_EXECUTION]: The skill utilizes command-line tools for verifying migration results.\n
- Evidence: Step 6 instructs the agent to use
curl -Ion every old URL to test redirects. This is a standard validation practice and is considered safe within the context of the skill's intended purpose.
Audit Metadata