marketing-social-pulse
Warn
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill contains a Preamble bash script that discovers an installation directory by searching multiple candidate paths including the user's home directory. It then executes a binary named kaito-skills-update-check from the resolved path. Executing code from a dynamically computed path presents a security risk if the file system can be influenced by malicious actors or if the environment variables point to untrusted locations.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external Twitter data via the kaito_advanced_search tool, creating a vulnerability to indirect prompt injection attacks where malicious content in tweets could influence the agent's behavior.\n
- Ingestion points: External tweet content retrieved during the data gathering and drill-down stages via kaito_advanced_search.\n
- Boundary markers: Absent; the instructions do not specify the use of delimiters or provide warnings to the agent to treat the external content as potentially untrusted.\n
- Capability inventory: The skill utilizes several Kaito MCP tools for entity resolution, metrics gathering, account attribution, and narrative analysis.\n
- Sanitization: Absent; the skill does not perform any validation, filtering, or sanitization of the retrieved tweet data before it is processed for analysis.
Audit Metadata