stackbone-debug

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including log frames and error message metadata, creating a surface for indirect prompt injection where malicious instructions could be embedded in the data being triaged.
  • Ingestion points: The skill facilitates reading execution logs via stackbone logs tail and run metadata via stackbone runs get (referenced in SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided for the agent to use when processing these logs.
  • Capability inventory: The skill allows for the execution of diagnostic CLI commands, read-only database queries (stackbone db query), and storage listing across the workspace environment.
  • Sanitization: There is no evidence of sanitization or filtering logic applied to the log data before it is presented to the agent for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:58 PM
Security Audit — agent-trust-hub — stackbone-debug