The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a local Python script (scripts/login.py) to manage authentication steps and filesystem operations.
[CREDENTIALS_UNSAFE]: Session tokens are stored in plaintext in ~/.konecty/.env and ~/.konecty/credentials. This is the primary function of the skill and is protected by restricted directory permissions (0700).
[DATA_EXFILTRATION]: The skill transmits user identifiers and OTP codes to the Konecty API endpoint for verification.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection. 1. Ingestion points: JSON responses from the {host}/api/auth endpoints in scripts/login.py. 2. Boundary markers: Absent. 3. Capability inventory: Filesystem write access (ensure_env_file, ensure_credentials_ini) and outbound network requests. 4. Sanitization: Absent; the script directly interpolates API response data into configuration files.

konecty-session