Skills
skills/onsager-ai/dev-skills/web-testing/Gen Agent Trust Hub

web-testing

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git diff using a commit range provided via the DIFF_RANGE environment variable to determine which application routes require testing.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests untrusted data from git diffs. 1. Ingestion points: Output of git diff (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Browser automation (agent-browser), file system writes for screenshots (/tmp/l2-screenshots), and test file generation (apps/dashboard/tests/). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:41 PM
Security Audit — agent-trust-hub — web-testing