run-premortem
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODEEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided plans or decisions to generate failure modes. Ingestion points: The skill accepts user input as a 'plan or decision' to be analyzed. Boundary markers: No delimiters or ignore instructions are provided to wrap the user input. Capability inventory: The skill does not possess any code-execution, file system, or network capabilities. Sanitization: The skill does not perform any input sanitization or filtering.
- [NO_CODE]: The skill contains only natural language instructions and markdown documentation with no executable scripts or binaries.
- [EXTERNAL_DOWNLOADS]: The documentation includes instructions to download and install the skill from the author's GitHub repository.
Audit Metadata