deal-value-calc
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business metrics and assumptions to generate narrative reports and financial models.
- Ingestion points: Untrusted data enters the agent context through user responses to the 'Interview' section in
SKILL.md. - Boundary markers: The skill enforces a strict provenance labeling system (buyer-supplied, benchmark, rep-assumed) and a 10-point 'Quality gate' to verify data integrity.
- Capability inventory: Skill logic is restricted to text generation and mathematical calculations; no subprocess calls, file-write operations, or network exfiltration patterns were found.
- Sanitization: The skill mandates the use of clearly labeled placeholders for missing data and requires explicit disclosure of any unverified assumptions in the final output.
- [DYNAMIC_CONTEXT_INJECTION]: No shell execution or dynamic context injection patterns were identified. Exclamation marks used in the narrative templates within
references/business-case-template.mdare part of descriptive placeholders for document generation and do not constitute executable code. - [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths (e.g., .ssh, .aws), or unauthorized network operations were detected in the skill instructions or scripts.
Audit Metadata