The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from Bolna's external API through the list_violations.py script. This data is then processed by the agent. While this creates a potential surface for indirect prompt injection if violation descriptions contain malicious instructions, the risk is inherent to the skill's primary purpose of monitoring compliance flags. The skill also possesses capabilities to read local files and perform network operations via submit_violation_evidence.py, but these actions are restricted to interacting with the vendor's own API endpoints.

manage-violations