debugging-executions

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and process data from external workflow executions, which constitutes a surface for indirect prompt injection from potentially attacker-controlled workflow outputs.\n
  • Ingestion points: Data returned by the executions tool through actions such as run, debug, and get-resolved-node-parameters (SKILL.md).\n
  • Boundary markers: The instructions do not define delimiters or provide warnings for the agent to ignore instructions embedded within the execution data.\n
  • Capability inventory: The agent has capabilities to re-run workflows and inspect all resolved parameters, which could be influenced by malicious data.\n
  • Sanitization: There is no evidence of sanitization or filtering of the execution content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:12 PM
Security Audit — agent-trust-hub — debugging-executions