systems-thinking
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of analyzing external data (bug reports and system incidents).
- Ingestion points: The skill ingests untrusted data from the user in Step 1 (Iceberg Model Analysis), specifically where it asks to analyze 'What just happened? (The bug/incident)'.
- Boundary markers: The instructions lack requirements for using boundary markers, such as XML tags or unique delimiters, to separate user-provided input from the agent's internal instructions.
- Capability inventory: The skill has the capability to write its analysis to the file system at 'docs/strategic/SYSTEM_ANALYSIS.md'.
- Sanitization: There are no instructions provided to sanitize, escape, or validate the content of the system descriptions or incident reports before processing them.
Audit Metadata