seo-sitemaps
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external sitemap.xml and robots.txt files.
- Ingestion points: Data is retrieved via WebFetch from external URLs as defined in SKILL.md.
- Boundary markers: The instructions do not specify boundary markers or instructions to ignore instructions within the fetched data are present.
- Capability inventory: The skill has access to Bash, WebFetch, and the ability to execute local scripts.
- Sanitization: There is no evidence of sanitization for the external content before it is processed by the agent.
- [COMMAND_EXECUTION]: A verification command runs a local Node.js script via the shell.
- Evidence: The command
node ${CLAUDE_SKILL_DIR}/../../scripts/parse-robots-sitemap.mjs --url <u>in SKILL.md uses a placeholder for URLs. - Risk: This represents a potential command injection vector if the
<u>parameter is populated with unsanitized user input containing shell metacharacters.
Audit Metadata