pasta-risk
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to synthesize data from the previous six stages of the PASTA framework. 1. Ingestion points: Inputs include business assets, entry points, components, threats, vulnerabilities, and exploitability scores from prior analysis. 2. Boundary markers: The instructions do not specify the use of delimiters to separate ingested data from process instructions. 3. Capability inventory: The skill is limited to text analysis and report generation and has no access to tools for network communication, file modification, or command execution. 4. Sanitization: No validation or sanitization of the input data from previous stages is defined.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, binaries, or code files.
Audit Metadata