sailpoint-stuck-requests
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
sailCLI commands to perform administrative operations on the SailPoint Identity Security Cloud tenant. This includes switching environments and making API calls to list or modify the state of access requests. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it retrieves and interprets data from an external API.
- Ingestion points: Untrusted data is fetched from the
/v2025/access-request-statusendpoint (as documented inSKILL.md), which returns fields likenameanderrorMessagesthat may contain user-provided content. - Boundary markers: The skill's instructions do not include markers or warnings to separate the API response data from the agent's logical execution flow.
- Capability inventory: The skill has 'write' capabilities, as it can issue POST requests to cancel or force-close access requests via the CLI in
SKILL.mdandreferences/api-endpoints.md. - Sanitization: There is no indication of sanitization or validation performed on the retrieved API data before it is presented to the agent or used in subsequent logic.
Audit Metadata