sailpoint-stuck-requests
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from external data sources.
- Ingestion points: In
SKILL.md(Step 2), the agent parses JSON output from thesail api getcommand, which includes user-influenced fields such as access request names and error messages. - Boundary markers: No specific delimiters or instructions are used to isolate the API data from the agent's internal logic or instructions.
- Capability inventory: In
SKILL.md(Step 4), the agent can execute commands to cancel or force-close requests in the SailPoint tenant usingsail api postcalls. - Sanitization: The instructions do not define any sanitization or validation for the data received from the API before processing or display.
- [COMMAND_EXECUTION]: The skill workflow requires executing commands via the
sailCLI on the local system. This behavior is necessary for its primary function and is documented for the user.
Audit Metadata