term-sheet-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown documentation (SKILL.md, references/clause-analysis.md, and references/market-standards.md). It defines a workflow and logic for text analysis but contains no scripts (Python, JS, etc.) or system commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided legal documents, which constitutes an ingestion surface for untrusted data.
- Ingestion points: Text from VC term sheets provided by the user (as described in SKILL.md).
- Boundary markers (absent): There are no explicit markers or instructions to the agent to ignore instructions embedded within the analyzed document.
- Capability inventory: No capability to execute commands, perform network operations, or write to the file system was found in any skill file. The output is strictly limited to text responses within the agent's chat interface.
- Sanitization (absent): No sanitization or input validation logic is defined for the input data.
- [SAFE]: The skill functions as an educational framework for legal document review. It includes appropriate legal disclaimers and does not demonstrate any patterns associated with credential theft, data exfiltration, or persistence. All external sources cited (e.g., Cooley, Carta, NVCA) are reputable legal and financial data providers.
Audit Metadata