contract-and-proposal-writer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it interpolates untrusted user inputs directly into document templates.
- Ingestion points: User-provided inputs such as 'Scope summary', 'Parties', and 'Special requirements' are gathered in
SKILL.md(Step 1: Requirements Gathering) to populate the templates. - Boundary markers: Absent. The skill does not define specific delimiters or instructions for the agent to disregard potential instructions embedded within the user-supplied data.
- Capability inventory: The skill utilizes the local filesystem to execute validation and analysis scripts (
scripts/contract_clause_checker.py,scripts/contract_comparison_analyzer.py,scripts/proposal_cost_estimator.py) and generates structured Markdown output. - Sanitization: Absent. No explicit filtering, escaping, or validation mechanisms are described for user-provided text values before they are integrated into the final document draft.
Audit Metadata