win-aip-contract-sync
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute local shell scripts and CLI tools, including
scripts/local/sync_aip_contracts.sh,scripts/local/check_aip_contracts_drift.sh,git, andpnpm. These operations are performed using absolute paths on the local filesystem, which grants the agent authority to run executable code from the user's local environment. - [PROMPT_INJECTION]: The workflow involves reading and following instructions from various local documentation files such as
win/AGENTS.mdandaipodcasting/docs/references/*.md. This creates an indirect prompt injection surface where content within those files could influence the agent's behavior during the sync process. - Ingestion points: Local documentation and reference files including
win/AGENTS.md,aipodcasting/AGENTS.md, and multiple files indocs/references/directories (e.g.,api-endpoint-implementation.md). - Boundary markers: Absent; the agent is instructed to use these files as primary references for its operating rules without explicit instructions to ignore embedded commands.
- Capability inventory: The skill possesses the capability to execute shell scripts, perform Git operations, and invoke Node.js tooling (
pnpm). - Sanitization: No evidence of sanitization or validation of the content within the referenced documentation files before processing.
Audit Metadata