crypt
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external and potentially untrusted data, such as vulnerability reports from the 'Sentinel' agent and user-provided security requirements, which it uses to generate cryptographic specifications.
- Ingestion points: According to the collaboration patterns in
SKILL.md, the skill receives vulnerability data and requirements from multiple sources includingSentinel,Canon[regulatory], and theUser. - Boundary markers: The instructions do not specify the use of clear delimiters or instructions for the agent to ignore potentially malicious embedded content within the processed reports.
- Capability inventory: While the skill itself focuses on design, its output directly influences the 'Builder' agent (which handles implementation) and the 'Scaffold' agent (which handles infrastructure configuration).
- Sanitization: The provided instructions lack specific procedures for sanitizing, validating, or escaping input from external reports before it is used to generate designs.
Audit Metadata