contract-review
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted external contract files, which could contain adversarial instructions intended to manipulate the AI agent's analysis or subsequent actions.
- Ingestion points:
scripts/contract_analyzer.pyreads and processes the content of user-provided contract files (e.g., contract.txt or agreement.md). - Boundary markers: There are no explicit boundary markers, escaping mechanisms, or instructions to ignore embedded commands within the analyzed contract text.
- Capability inventory: The skill relies on local Python scripts to perform regex-based pattern matching for clause identification and risk classification. It does not have access to the network or arbitrary command execution during its automated analysis.
- Sanitization: The analysis output includes raw 'text_snippet' fields from the input contract, which are passed to the agent without sanitization or filtering.
Audit Metadata