The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill audits external websites by fetching their HTML, which introduces a potential surface for indirect prompt injection if those sites contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill reads rendered_dom and raw_html from the target website (SKILL.md).
Boundary markers: Absent. No specific delimiters or warnings to ignore embedded instructions are provided for the ingested data.
Capability inventory: The skill utilizes Read, Grep, Glob, WebFetch, and Bash tools (SKILL.md).
Sanitization: Absent. The skill does not specify sanitization methods for the ingested HTML content.
[COMMAND_EXECUTION]: The skill uses a local script to perform complex hreflang validation tasks.
Evidence: It executes node ${CLAUDE_SKILL_DIR}/../../scripts/hreflang-check.mjs --url <u> as part of the verification process described in SKILL.md.

seo-international