distill
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it analyzes user-provided source code to identify and suggest deletions for 'dead code' and 'complexity'.
- Ingestion points: User-provided backend source code files targeted for the 'distill' process as described in
SKILL.md. - Boundary markers: No explicit boundary markers (e.g., XML tags) or instructions to disregard instructions embedded within comments/strings of the analyzed code are defined in the process steps.
- Capability inventory: The skill uses
axiom:scanand qualitative assessment to generate findings that recommend modifications or deletions to the codebase. - Sanitization: The skill lacks mechanisms to sanitize or ignore instructions that may be hidden in code comments or documentation which could influence the agent's logic or the content of the generated findings.
Audit Metadata