The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a local script scripts/report_publish.py to generate final HTML and PDF reports from the markdown analysis.
[INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it fetches and interprets content from external websites.
Ingestion points: The skill performs webfetch operations on URLs provided by the user and all external links found on those pages.
Boundary markers: No delimiters or safety instructions are defined to separate untrusted external content from the agent's internal logic.
Capability inventory: The skill utilizes network access via webfetch and local command execution via python.
Sanitization: The instructions do not include steps to sanitize or validate the content retrieved from external sources.

external-linking