har-debugger

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 processes external data from .har files that could contain malicious instructions.\n
  • Ingestion points: The har_file input parameter allows the agent to read external JSON data (SKILL.md).\n
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to treat the HAR content strictly as data.\n
  • Capability inventory: The skill parses the HAR file and extracts text from potentially attacker-controlled fields such as status texts, response headers, and response bodies (SKILL.md).\n
  • Sanitization: Absent. The workflow extracts and correlates content directly without filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 07:06 PM
Security Audit — agent-trust-hub — har-debugger