secretary
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and summarize outputs from background research agents using tools like agent_output and manage_threads.
- Ingestion points: Untrusted data enters the agent context through the agent_output and manage_threads(action='get_output') tools as described in SKILL.md.
- Boundary markers: The documentation mentions turn separators ('---') for thread history, but lacks specific instructions for the agent to ignore or neutralize instructions embedded in the retrieved text.
- Capability inventory: The skill allows the agent to manage workspaces (create, stop, delete) and dispatch background agents with full code execution capabilities via the ptc_agent tool in SKILL.md.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the content retrieved from external agent threads before it is processed by the main agent.
Audit Metadata