extract-secrets

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes JavaScript source code from external, potentially untrusted URLs provided by the user. This creates an attack surface for indirect prompt injection, where malicious instructions hidden in the code could attempt to influence the agent's behavior.
  • Ingestion points: The target URL is accepted via skill_session_create, and code is processed by skill_decompile_spa.
  • Boundary markers: The instructions do not define specific delimiters to separate untrusted web content from the agent's core instructions.
  • Capability inventory: The agent can perform network requests to the target site and the Crawlio API via the mcp__crawlio__call tool.
  • Sanitization: The instructions explicitly require the agent to redact sensitive values before they are included in findings or reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:06 AM
Security Audit — agent-trust-hub — extract-secrets