The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from arbitrary external URLs, which creates a surface for indirect prompt injection attacks where malicious instructions on a web page could attempt to influence agent behavior.\n
Ingestion points: Untrusted content is ingested from the URLs specified in the urls parameter as defined in SKILL.md.\n
Boundary markers: The instructions do not define specific delimiters or instructions to treat the external content as data rather than instructions.\n
Capability inventory: The skill uses curl to interact with the Octen API at api.octen.ai.\n
Sanitization: No specific sanitization or filtering of the extracted content is described before it is provided to the agent.\n- [COMMAND_EXECUTION]: The skill utilizes the curl utility to perform HTTP POST requests to the api.octen.ai endpoint. This is a standard implementation for interacting with external APIs and is consistent with the skill's stated purpose.

octen-extract