The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation references an external setup guide located at https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md. This introduces a dependency on content from an unverified third-party repository which could change or contain malicious instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied messages and LLM responses, creating a surface for indirect prompt injection attacks.
Ingestion points: User-provided text in the messages array of the curl command examples in SKILL.md.
Boundary markers: None present; the examples do not demonstrate the use of delimiters or instructions to ignore embedded commands within the content.
Capability inventory: The skill performs network operations via curl to send data to external API endpoints.
Sanitization: There is no evidence of data validation or sanitization before message content is transmitted to the $OMNIROUTE_URL endpoint.

omniroute-chat