security-requirement-extraction
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of threat models and business context to generate security requirements.
- Ingestion points: The skill ingests threat data as described in
SKILL.mdand uses theThreatInputdata structure defined inresources/implementation-playbook.md. - Boundary markers: There are no explicit instructions for the agent to use delimiters or specific boundary markers to distinguish between threat data and potentially malicious instructions embedded within the input models.
- Capability inventory: The skill's primary function is text-based content generation (user stories, requirements, test specifications) and does not include capabilities for file system modification, shell execution, or network access.
- Sanitization: The provided Python templates in the playbook use string interpolation (
.format()) to incorporate threat details into generated requirements without visible sanitization or filtering logic.
Audit Metadata