skills/howells/arc/verify/Gen Agent Trust Hub

verify

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local build and test scripts such as npm run build, vitest, and jest. These are standard development tasks but involve running code defined in the project's own configuration files.\n- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it ingests output from compilers, linters, and grep searches.\n
  • Ingestion points: Tool outputs from build, typecheck, lint, and test processes, as well as raw file contents identified during grep-based secret and debug log audits.\n
  • Boundary markers: Absent; the workflow summarizes output without applying delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: Subprocess execution of detected package managers and git commands.\n
  • Sanitization: Absent; tool outputs are reported directly into the final summary without validation or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 09:28 AM