asset-fallback-strategy

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied or externally-sourced data to generate asset fallback plans, creating a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through the 'Recipe brief' and 'Failed asset + reason' inputs defined in the input schema of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions to the model to ignore potentially malicious instructions embedded within the processed briefs.
  • Capability inventory: The skill is scoped to planning and routing; it does not contain capabilities for direct shell execution, network requests, or file system modifications.
  • Sanitization: There are no defined processes for sanitizing, escaping, or validating the input data before it is interpolated into the planning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:09 PM