The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest user-defined feature configurations and app data from external API endpoints, which could contain malicious instructions designed to influence the agent's logic.
Ingestion points: The agent retrieves data from GET /api/features/config/ and GET /api/features/apps/ as described in SKILL.md.
Boundary markers: The skill does not provide specific instructions or delimiters to ensure the agent ignores or treats the retrieved feature values or app names as untrusted data.
Capability inventory: The agent has the ability to modify user and platform state via POST requests to config/, bulk-config/, and provision/ endpoints.
Sanitization: No sanitization or validation logic is specified for the data returned from the API before the agent interprets it.
[COMMAND_EXECUTION]: The skill includes instructions and examples for executing shell-based curl commands to interact with the vendor's API, which the agent is expected to use to perform its tasks.

iblai-api-feature