skills/fittings-sh/skills/qr-encode/Gen Agent Trust Hub

qr-encode

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes arbitrary text input through its text parameter to generate QR codes, creating a surface for indirect prompt injection if the output is processed by downstream systems or users.\n
  • Ingestion points: The text field in the POST request defined in SKILL.md.\n
  • Boundary markers: Absent.\n
  • Capability inventory: Network communication with fittings.sh and local file system read access for integrity checks.\n
  • Sanitization: None present; the skill encodes provided text directly into the QR matrix.\n- [EXTERNAL_DOWNLOADS]: The skill documentation suggests downloading an execution script from fittings.sh via curl. At runtime, the script also fetches an integrity hash from the same domain to verify its source code.\n- [DATA_EXFILTRATION]: The execution script accesses the FITTINGS_PRIVATE_KEY environment variable to sign payment challenges. These signed authorizations are then transmitted back to the fittings.sh API to settle transaction costs for the QR generation service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 05:17 AM