assess-problem-wickedness
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were identified. The skill consists entirely of natural language instructions and YAML-based contracts for a classification task. It does not include scripts, tools, or remote references.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface that could be used for indirect prompt injection. 1. Ingestion points: Untrusted input enters the agent context through problem_statement and stakeholder_views as defined in SKILL.md. 2. Boundary markers: There are no delimiters or instructions to ignore embedded commands. 3. Capability inventory: No subprocess calls, network operations, or file-system writing capabilities were identified in the skill. 4. Sanitization: The skill does not implement validation or escaping for the processed input.
Audit Metadata