The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill contains a reference to a malicious URL detected by security scanners.
Evidence: The URL https://fitprofessionals.net is listed in references/directory-list.md and references/submission-tracker-template.csv as a target for directory submissions. Automated scans flagged this domain as malicious (URL:Blacklist|URC1A1CADBA41B2847-0200|urlb).
[COMMAND_EXECUTION]: The skill instructions promote the execution of shell commands to interact with external web resources.
Evidence: In SKILL.md, users are instructed to verify backlinks using curl -sIL https://directory.com/your-listing | grep -i rel=. Executing network-based shell commands against arbitrary external URLs is a risky practice that can be exploited if target domains are malicious or if the command is improperly sanitized.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external files and user inputs, which could be used to influence the agent's behavior.
Ingestion points: The workflow in SKILL.md directs the agent to read context from files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the ingestion process.
Capability inventory: The skill instructions involve the use of curl for network operations (File: SKILL.md).
Sanitization: There is no evidence of validation or filtering for the external content being processed.

directory-submissions