change-request
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Data Ingestion Surface: The skill processes user-provided change descriptions to generate structured output. This interaction with external data is a typical characteristic of agent skills, although it represents the primary surface where indirect instructions could be introduced.\n
- Ingestion points: User input is passed via the $ARGUMENTS variable in SKILL.md.\n
- Boundary markers: The skill does not explicitly define delimiters for user input, relying on the agent's natural language understanding to separate input from instructions.\n
- Capability inventory: The skill references potential interactions with ITSM tools, project trackers, and chat platforms if connectors are enabled.\n
- Sanitization: No explicit sanitization or validation of the input text is defined within the instruction set.\n- Tool Integration Framework: The instructions mention interactions with external services like ITSM and project management tools. These are described as conditional capabilities that rely on the platform's existing connector infrastructure to perform automated tasks.
Audit Metadata