The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an Indirect Prompt Injection vulnerability surface by encouraging the agent to ingest and obey instructions from external sources.
Ingestion points: The workflow described in SKILL.md directs the agent to fetch service lists from https://ctxly.com/services.json and then follow URLs to retrieve documentation from third-party sites like moltbook.com.
Boundary markers: No specific delimiters or safety instructions are provided to help the agent distinguish between its core instructions and potentially malicious commands embedded in the fetched markdown files.
Capability inventory: The skill utilizes curl for network requests and expects the agent to parse and execute logic found in external files.
Sanitization: The skill lacks mechanisms to sanitize or validate the content of the external documentation before it is integrated into the agent's context.
[EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of external data via command-line tools.
Fetches a directory of services from ctxly.com using curl.
Dynamically fetches skill.md files from third-party domains defined in the directory metadata.

agent-directory