atlas-weave
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the primary
argument-hintto define coding tasks. This input is then propagated to multiple sub-agents (such as the planner and coder) which have the capability to modify files and execute shell commands. - Ingestion points: The user's "rough multi-file coding request" enters the agent context at the DECOMPOSED stage and is stored in a task packet.
- Boundary markers: The instructions specify that the intent is frozen into an immutable task packet to prevent runtime manipulation of the goal, though the content itself remains untrusted input.
- Capability inventory: The skill and its sub-runs utilize high-privilege tools including
Write,Edit, andBash. - Sanitization: No explicit sanitization, escaping, or validation of the user-provided request is described before it is interpolated into prompts for the planning and coding agents.
- [COMMAND_EXECUTION]: The orchestrator performs system command execution using the
Bashtool for several management and verification tasks. - It executes
free -mto monitor system memory availability, which is used as a live admission input for wave scheduling. - It executes a user-provided
verify_cmdto validate changes on the merged worktree during the INTEGRATE stage. - It executes local Python modules via
python3 -cusing a configuredPYTHONPATHthat points to directories relative to the skill directory.
Audit Metadata