pasta-attack-sim
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process data from previous threat modeling stages (Stages 1 through 5), serving as an external data entry point.
- Ingestion points: Vulnerability inventory (Stage 5), business assets (Stage 1), entry points (Stage 2), and threat catalog (Stage 4) mentioned in the Prerequisites section.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed data are provided.
- Capability inventory: No specific tools or command execution capabilities are defined in the provided markdown, though the agent's default environment capabilities remain available.
- Sanitization: The skill lacks instructions for input validation or sanitization mechanisms to handle potentially malicious data from previous stages.
Audit Metadata