The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes requests to api.serply.io, a well-known search API. This communication is restricted to the skill's stated purpose of retrieving search data.
[COMMAND_EXECUTION]: The instructions include curl examples for interacting with the Serply API. These commands are benign and do not involve executing untrusted remote code or accessing sensitive system resources.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted search results from the internet. Ingestion point: JSON responses from api.serply.io (documented in SKILL.md). Boundary markers: Absent. Capability inventory: curl for API interaction. Sanitization: Not explicitly mentioned in instructions. The risk is low as there are no exploitable sinks like dynamic code execution.

serply-search