The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill includes a reference to a domain flagged as malicious by security scanners.
Evidence: The URL https://fitprofessionals.net is included in the directory listings within references/directory-list.md and references/submission-tracker-template.csv. This domain has been identified as blacklisted by automated safety checks. Recommending malicious links for product submissions can lead to phishing, credential theft, or malware exposure.
[PROMPT_INJECTION]: The skill instructs the agent to ingest external context from local files without providing boundary markers or sanitization instructions.
Ingestion points: SKILL.md directs the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding.
Boundary markers: None present to distinguish ingested data from instructions.
Capability inventory: The skill is composed of documentation and templates with no direct execution of shell scripts or binaries, which significantly limits the impact of an injection attack.
Sanitization: No filtering or validation logic is defined for the ingested context.
[NO_CODE]: The skill is entirely descriptive and does not ship with any executable scripts, binaries, or source code files.

directory-submissions