The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The script scripts/onboarding.py contains a hardcoded Base64-encoded identifier _LOGIN_FIXED_UID. This string decodes to a JSON object used as a default value for authentication headers when interacting with vendor services.
[COMMAND_EXECUTION]: The skill instructions require the agent to execute shell commands to run local Python scripts (scripts/seerfar_ozon_keyword_back_search.py and scripts/onboarding.py). These commands incorporate user-supplied parameters, creating a potential for argument injection if the JSON input is not carefully handled by the agent.
[DATA_EXFILTRATION]: The skill collects product SKUs and keyword lists provided by the user and transmits them to vendor-controlled domains (tool-gateway.linkfox.com, api.linkfox.com). Additionally, the main script automatically persists full API response data to the local filesystem under the linkfox/ directory.
[EXTERNAL_DOWNLOADS]: The scripts/onboarding.py script requires the installation of external Python packages, specifically requests, qrcode, and pillow, to support its login and payment QR code generation features.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external product data and user keywords.
Ingestion points: Product SKU IDs (skuIds) and inclusion/exclusion keyword lists (includeKeywords, excludeKeywords) ingested from user prompts.
Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate user-supplied data from the instruction context.
Capability inventory: The skill possesses capabilities for network communication and local file writes via the provided Python scripts.
Sanitization: No explicit sanitization, filtering, or validation logic for the input strings is provided in the instructions or scripts.

linkfox-seerfar-ozon-keyword-back-search