still-qa

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted text from the --prompt argument and the --bible file, which are interpolated directly into the system prompt for the VLM judge. \n
  • Ingestion points: scripts/judge.py reads the --prompt CLI argument and the file content from the path in --bible. \n
  • Boundary markers: Absent. The data is concatenated with simple text labels without delimiters. \n
  • Capability inventory: scripts/judge.py performs file reads (open) and network operations (urllib.request). \n
  • Sanitization: Absent. No escaping or filtering is applied to the inputs. \n- [DATA_EXFILTRATION]: The script scripts/judge.py reads local file data and transmits it to a network endpoint. \n
  • It reads images and text files specified by CLI arguments. \n
  • It sends this content, plus the VLM_API_KEY environment variable, to the URL specified by --endpoint. \n
  • This allows for the exfiltration of local assets to non-whitelisted domains if the endpoint is changed from its default.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 08:12 PM