structured-red-team
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The analyzed skill file consists entirely of Markdown instructions and YAML metadata. It does not include any Python scripts, Node.js code, shell commands, or binary executables.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content, specifically 'artifacts' and 'threat models', which could contain embedded malicious instructions intended to influence the agent's behavior during the red-teaming process.
- Ingestion points: The skill accepts 'artifact', 'threat_model', and 'probe_scope' as required inputs defined in the YAML input contract within SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the artifacts are provided in the execution protocol.
- Capability inventory: This skill itself has no direct capabilities (network, file-system, or subprocess access). It relies entirely on loading and delegating to other skills like 'execute-probe' and 'map-threat-surface'.
- Sanitization: There are no instructions for validating, escaping, or sanitizing the input data before it is processed by the agent or passed to subsequent skills.
Audit Metadata