paw-mkt-psychology

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to set up the agent-browser tool to enable live website audits. This reference targets an official repository from a trusted organization for legitimate research capabilities.
  • Evidence: Installation command for https://github.com/vercel-labs/agent-browser in references/shared-patterns.md.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources when performing live website audits or reviewing existing codebases, which creates a surface for indirect prompt injection.
  • Ingestion points: Context B (Existing Codebase) and Context C (Live Website URL) described in references/shared-patterns.md.
  • Boundary markers: Not explicitly defined for external content ingestion.
  • Capability inventory: The skill is scoped to reading local files and browser-based research; no high-risk command execution or file-write capabilities were identified in the provided scripts.
  • Sanitization: No explicit validation or filtering of external content is documented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 02:59 PM