model
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow involves ingesting and analyzing untrusted data from the application codebase, including configuration files, manifests, and source code, to build a threat model.
- Ingestion points: Step 1 (Discovery) scans docker-compose files, k8s manifests, and service configs. Step 5 (Identify Mitigations and Gaps) searches the entire codebase for security controls.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the codebase content.
- Capability inventory: The skill has the capability to read any file in the repository and write output (Mermaid diagrams, JSON models, Markdown reports) to the
.appsec/model/directory. - Sanitization: There is no evidence of sanitization or escaping of the content ingested from the codebase before it is interpolated into the agent's context for STRIDE analysis or attack tree generation.
Audit Metadata