tos-clause-scanner
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or credential harvesting detected. The skill is entirely composed of text-based instructions for document analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted legal documents, which presents a surface for indirect prompt injection.
- Ingestion points: Document text or file content provided by the user as input to the Agent (referenced in SKILL.md).
- Boundary markers: The skill does not explicitly define markers or delimiters to isolate the untrusted document text from the agent's instructions.
- Capability inventory: No capabilities for network access, file system writing, or subprocess execution are granted or referenced in the skill instructions.
- Sanitization: The instructions do not define specific sanitization, escaping, or filtering for the input text.
Audit Metadata