The Agent Skills Directory

[SAFE]: The skill interacts with a legitimate vendor service at https://api.octen.ai. The use of curl for API requests is functional and transparently documented.
[COMMAND_EXECUTION]: The skill uses curl as its primary method for fetching data from the external search service.
[INDIRECT_PROMPT_INJECTION]: As an image search tool, the skill ingests data from the web which could potentially contain malicious instructions.
Ingestion points: External metadata retrieved from search results, including description, title, and html_snippet fields in SKILL.md.
Boundary markers: None defined to isolate external search result data from the agent's instructions.
Capability inventory: Network access via curl to the octen.ai domain.
Sanitization: No explicit content sanitization or validation of the search metadata is described in the instruction set.

octen-image-search