The Agent Skills Directory

[DATA_EXFILTRATION]: The script scripts/update.py reads local configuration files containing sensitive credentials at ~/.konecty/.env and ~/.konecty/credentials. This is the expected behavior for the Konecty integration to authenticate its API requests.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data. 1. Ingestion points: The patch and update commands in scripts/update.py take data from CLI arguments. 2. Boundary markers: Absent. The instructions do not define boundaries for external data. 3. Capability inventory: The script performs network operations (HTTP PUT/POST) to the Konecty API. 4. Sanitization: No filtering or sanitization is applied to the input JSON data before it is sent to the server.

konecty-update