orchestrate-with-handoff

Pass

Audited by Gen Agent Trust Hub on Oct 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon instructions found in external documents, including a user-provided handoff document, specifications, and tickets. These files represent untrusted data sources that could contain embedded instructions intended to manipulate the agent's behavior during the orchestration process.
  • Ingestion points: The skill reads a 'handoff document' from a user-provided path, as well as 'specs' and 'tickets' referenced within that document.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the content of these documents as data rather than instructions.
  • Capability inventory: The skill invokes the /orchestrate-effort command, which likely involves file system modifications (pull requests, branch management) based on the input content.
  • Sanitization: No sanitization or validation of the external document content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 20, 2026, 06:46 AM