The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Matomo Reporting API instances, such as page titles, search keywords, and referrers. This data is externally controlled and could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: API response data processed by matomo_report.py (referenced in SKILL.md).
Boundary markers: None specified in the instructions for separating API data from prompt instructions.
Capability inventory: The skill can perform network operations via the Matomo API and execute shell commands via the claude-seo script runner.
Sanitization: While the skill implements an SSRF guard and DNS pinning for the Matomo instance URL, there is no mention of sanitizing or escaping the text content returned by the API before it is presented to the AI agent.
[COMMAND_EXECUTION]: The skill executes local Python scripts (matomo_auth.py and matomo_report.py) through a central runner script located at ${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo.
Evidence: The Routing section in SKILL.md defines several commands that map to the execution of these internal scripts.

seo-matomo