playwright-form-validation

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external websites, which presents a risk of indirect prompt injection.\n
  • Ingestion points: Untrusted content is ingested from user-provided URLs using the mcp__playwright__browser_snapshot tool as seen in SKILL.md and references/detailed-workflow.md.\n
  • Boundary markers: There are no specified delimiters or instructions to ignore embedded malicious content within the page text.\n
  • Capability inventory: The agent is granted high-risk capabilities including Bash, Write, and Read, which could be abused if malicious instructions are successfully injected via a website.\n
  • Sanitization: No sanitization or filtering logic is provided for the ingested snapshot content before processing.\n- [COMMAND_EXECUTION]: The skill documentation instructs the agent to use the Bash tool to run a vendor-provided Python script (scripts/parse_validation_errors.py). While this script is legitimate and uses only standard libraries, the general Bash capability provides a broad execution surface that requires careful handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:24 PM