skills/irpsv/ai-bro/bro-debug/Gen Agent Trust Hub

bro-debug

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted data.
  • Ingestion points: The subagent /debugger is instructed to read code, search the repository, and analyze logs/test outputs (SKILL.md).
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to disregard potential commands embedded within the source files or logs it reads.
  • Capability inventory: The agent has capabilities to read any file in the repository and execute read-only CLI commands (SKILL.md).
  • Sanitization: No sanitization or validation logic is defined for the content ingested from the external environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 01:44 PM
Security Audit — agent-trust-hub — bro-debug