sailpoint-access-request-investigator
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
sailCLI to perform environment management and API interactions. It executes commands such assail environment list,sail api get, andsail api postto retrieve status information and perform request cancellations. - [PROMPT_INJECTION]: The skill processes JSON data returned from the SailPoint API. This creates a surface for indirect prompt injection if an attacker can manipulate fields within the SailPoint environment (e.g., identity names or error messages) to include instructions for the AI agent.
- Ingestion points: API responses from
/v2025/access-request-statusand/v2025/public-identitiesare processed inSKILL.md. - Boundary markers: The skill does not explicitly use delimiters or specialized instructions to isolate the external data from the system prompt.
- Capability inventory: The skill has the capability to execute
sail api postcommands which can modify state (cancel/close requests) based on the processed data. - Sanitization: The skill instructions recommend stripping CLI log metadata before parsing JSON, but do not specify input validation or instruction filtering for the data content.
Audit Metadata