sailpoint-transform-debugger

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external sources that could contain malicious instructions. Ingestion points: The skill retrieves transform definitions and identity data via 'sail api get' and 'sail transform download' commands. Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between data and instructions within the API responses. Capability inventory: The agent can execute powerful commands including 'sail transform upload' and 'sail api put' to modify system configurations. Sanitization: There is no evidence of data sanitization or validation performed on the API responses before processing.
  • [COMMAND_EXECUTION]: The skill executes several 'sail' CLI commands to manage environments and transforms. This is the primary intended behavior of the tool.
  • [EXTERNAL_DOWNLOADS]: The skill requires the SailPoint CLI as a prerequisite, which is a well-known tool hosted in the official 'sailpoint-oss' repository on GitHub.
  • [DATA_EXFILTRATION]: The skill accesses sensitive identity and account information from the SailPoint tenant. This data is used locally for tracing transform logic and is not transmitted to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 11:29 AM