The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill includes an extensive reference list of over 200 external directory URLs for product submissions. One specific domain, fitprofessionals.net, has been blacklisted by automated security scanners.\n- [COMMAND_EXECUTION]: The instructions direct the agent to use curl to verify backlink status on external directory listing pages, which involves network operations based on user-supplied or external URLs.\n- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its ingestion of external marketing context.\n
Ingestion points: The agent is instructed to read context from files such as product-marketing.md, .agents/product-marketing.md, and .claude/product-marketing.md.\n
Boundary markers: Absent. The skill does not define specific delimiters or instructions to treat the content of these context files as untrusted or to ignore embedded commands.\n
Capability inventory: The skill possesses the capability to fetch external web content using curl and parse it using grep.\n
Sanitization: Absent. No validation or sanitization is performed on the ingested marketing data before it is interpolated into the agent's prompt for description generation.

directory-submissions