The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the domain fitprofessionals.net within references/directory-list.md and references/submission-tracker-template.csv. This domain is currently blacklisted by automated scanners as malicious, posing a significant risk of phishing or malware exposure to users following the submission guides.
[EXTERNAL_DOWNLOADS]: Automated reputation scanners flagged the file references/submission-tracker-template.csv as malicious (FileRepMalware), indicating that the file contains patterns or metadata associated with known threats.
[COMMAND_EXECUTION]: The instructions in SKILL.md suggest that users or agents run shell commands (e.g., curl -sIL) to verify backlinks on external directories. This workflow encourages interaction with potentially untrustworthy or malicious third-party servers identified in the provided directory lists.
[PROMPT_INJECTION]: The skill is designed to read product marketing context from local files like .agents/product-marketing.md without implementing boundary markers or sanitization procedures. This creates a surface for indirect prompt injection where an attacker could control agent behavior by injecting malicious instructions into the product marketing documentation. * Ingestion points: .agents/product-marketing.md (checked during readiness assessment) * Boundary markers: Absent * Capability inventory: Suggested use of shell commands (curl) for verification * Sanitization: Absent

directory-submissions