qc-uiux
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes specific local scripts via shell commands for UI auditing:
node skills/visual-qa/assets/route-shots.mjs <base-url> --auditandpython3 fdk/tools/build-design-showcase.py. These appear to be utility scripts integrated into the agent's environment. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to how it processes external data.
- Ingestion points: The skill ingests raw DOM data, CSS, console logs (
error,pageerror), and network response metadata from a user-provided<base-url>as part of the audit process (documented in W01 and RULE-06). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the ingested web content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill is authorized to execute internal scripts and write report drafts to the
llmwiki/directory. - Sanitization: The skill lacks specified sanitization, filtering, or escaping mechanisms for the data retrieved from external URLs before passing it to the LLM for evaluation.
Audit Metadata