skills/lvlup-sw/axiom/audit/Gen Agent Trust Hub

audit

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by processing untrusted data from an analyzed codebase through multiple specialized qualitative skills.
  • Ingestion points: Codebase files and directories resolved through the scope argument in SKILL.md.
  • Boundary markers: The orchestration process does not specify the use of delimiters or explicit instructions to treat code content as untrusted data.
  • Capability inventory: The skill invokes several specialized agents (critique, harden, distill, verify, humanize) to perform qualitative assessments on the ingested content.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the codebase content before it is processed by the agent pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 06:39 PM
Security Audit — agent-trust-hub — audit