The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes common shell utilities such as curl and grep, along with a specific isagentready CLI tool, to perform read-only verification of a website's structured data status and HTTP response codes. These commands are intended to be executed against the user's target domain for auditing purposes.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing HTML content from external websites to identify and fix structured data issues. This creates an inherent ingestion surface where the agent could potentially be exposed to malicious instructions embedded in third-party website content.
Ingestion points: HTML responses retrieved from user-specified URLs via the curl command or the isagentready tool, as described in SKILL.md and references/checkpoints.md.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to separate site content from the agent's internal reasoning or rules.
Capability inventory: The agent is granted the capability to modify local project files (adding JSON-LD blocks) and execute shell commands for verification based on the results of the external data analysis.
Sanitization: There are no explicit sanitization or filtering steps mentioned for the ingested HTML content before it is processed by the agent.

structured-data