hurry-up
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill collects and synthesizes reports from subagents and repository status to prepare a session handoff. This process creates an attack surface where instructions embedded in subagent output or local file changes could influence the agent's final report or the behavior of the next agent receiving the handoff.\n
- Ingestion points: The agent ingests reports received from subagents via
SendMessageor native messaging tools, and state information fromgit statusandgit diff.\n - Boundary markers: The skill does not explicitly instruct the agent to use delimiters or boundary markers to isolate the untrusted subagent content from the agent's own synthesis instructions.\n
- Capability inventory: The agent has the capability to perform
git commit(when authorized) and invoke thetask-handoffskill.\n - Sanitization: The skill lacks requirements for sanitizing, escaping, or validating the content gathered from subagents or the local file system before it is interpolated into the final handoff synthesis.
Audit Metadata