reproduce-bug
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it retrieves and follows instructions from untrusted sources (GitHub issue descriptions and comments).
- Ingestion points: Reads GitHub issue #$ARGUMENTS and its associated comments (Phase 1 and Phase 2).
- Boundary markers: Absent. The skill lacks delimiters or instructions that would prevent the agent from executing malicious commands embedded within the GitHub issue text.
- Capability inventory: The skill possesses significant capabilities including browser navigation, clicking elements, form filling, taking screenshots, and capturing console logs through the Playwright MCP plugin.
- Sanitization: No evidence of sanitization, filtering, or validation of the issue content before it is used to direct the Playwright browser actions.
Audit Metadata