The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the domain fitprofessionals.net in references/directory-list.md and references/submission-tracker-template.csv. This domain has been flagged as malicious and blacklisted by automated security scanners.
[COMMAND_EXECUTION]: The workflow (SKILL.md) provides explicit instructions for the agent or user to execute network commands using curl to verify the status of external links (curl -sIL [URL] | grep -i rel=). Executing shell commands based on untrusted external directory listings poses a risk of command injection or interaction with malicious endpoints.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted local data.
Ingestion points: The instructions require the agent to read external context files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding (SKILL.md).
Boundary markers: No boundary markers or instructions to ignore embedded commands within these files are provided.
Capability inventory: The skill possesses the capability to execute network requests via curl and perform file system operations (SKILL.md).
Sanitization: There is no evidence of sanitization, validation, or filtering of the ingested context data.
[SAFE]: The licensing information and frontmatter structure follow standard conventions and do not contain malicious patterns.

marketing-directory-submissions