debug

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to read and follow a workflow defined in .agents/workflows/debug.md, which creates an indirect prompt injection surface.
  • Ingestion points: .agents/workflows/debug.md (referenced in SKILL.md).
  • Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore potentially malicious embedded instructions in the workflow file.
  • Capability inventory: The debugging workflow (reproduce, diagnose, fix, test) implies the use of file-read, file-write, and subprocess-execution capabilities.
  • Sanitization: Absent; the skill does not validate or sanitize the content of the referenced workflow file.
  • [NO_CODE]: The skill consists exclusively of instructions in markdown format and does not include any scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 03:17 AM
Security Audit — agent-trust-hub — debug