The Agent Skills Directory

[COMMAND_EXECUTION]: The file references/checks.md defines several shell command pipelines using curl, grep, sed, and python3 to extract JSON-LD and microdata from a user-provided $URL. These commands are used for data extraction and parsing, rather than executing arbitrary remote code.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites, creating a potential surface for indirect prompt injection where an attacker could place instructions in a site's schema markup.
Ingestion points: External data is brought into the agent's context through curl commands in references/checks.md.
Boundary markers: The instructions do not define specific delimiters or warnings to treat the fetched content as potentially adversarial data.
Capability inventory: The skill utilizes subprocess execution for curl, grep, sed, and python3 to process the ingested content.
Sanitization: There is no evidence of input validation or escaping for the content retrieved from external sources before it is processed by the agent.

schema-markup-audit