workflow-coordinator

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's documentation and reference files (e.g., SKILL.md, references/handoff-validation.md) provide shell commands for generating trace identifiers and performing data validation using python3 -c one-liners.
  • [PROMPT_INJECTION]: The skill facilitates the processing of data from external workflows, creating a surface for indirect prompt injection.
  • Ingestion points: Natural language data is ingested through schema fields such as handoff.context.summary, handoff.context.original_prompt, and handoff.payload.working as described in references/universal-handoff-schema-v3.0.json.
  • Boundary markers: The instructions for receiving agents in SKILL.md do not include explicit delimiters or safety instructions to treat ingested strings as non-executable data.
  • Capability inventory: The skill is capable of local file system interaction (reading and writing to session and log files) and executing shell commands for validation purposes.
  • Sanitization: There is no evidence of sanitization or escaping logic applied to the natural language fields before they are presented to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:18 PM
Security Audit — agent-trust-hub — workflow-coordinator