tprm
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted external data provided by third parties, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests vendor SOC 2 reports, Data Processing Agreements (DPAs), security questionnaires, and contract addenda provided by the user (SKILL.md, references/soc2-report-review.md).
- Boundary markers: No explicit boundary markers or instructions to isolate or disregard potential instructions embedded within the analyzed documents are present.
- Capability inventory: The skill has no dangerous capabilities; it does not utilize shell commands, network requests, or file system modifications.
- Sanitization: No sanitization, validation, or filtering mechanisms are defined for the external text being processed.
Audit Metadata