syncing-aidlc-workflows
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the
aidlc-workflowsproject fromgithub.com/awslabs/aidlc-workflows. This is used to retrieve the latest tools and documentation for integration into the user's project. The skill supports both git cloning and direct tarball downloads from GitHub's codeload service. - [REMOTE_CODE_EXECUTION]: Executes a build script (
node build/kiro-ide/build.js) on the content downloaded from the AWS Labs repository when the 'kiro' tool is selected. This is performed within a temporary directory to generate the necessary artifacts before they are integrated into the host project. - [INDIRECT_PROMPT_INJECTION]: The skill processes markdown documentation from a remote source for translation. This creates a surface where instructions embedded in the external files could potentially influence the agent's behavior during the reading and translation process.
- Ingestion points: Files downloaded from the
awslabs/aidlc-workflowsrepository to the.aidlc-sync/base/directory, which are subsequently read by the agent. - Boundary markers: None; the agent is instructed to read the raw markdown files from the
base/directory for translation. - Capability inventory: The skill has access to
Bash,Write,Edit,Glob,Grep, andReadtools. - Sanitization: The skill does not perform content sanitization or filtering on the ingested markdown before the agent processes it.
- [COMMAND_EXECUTION]: Utilizes several shell scripts (
lib/*.sh) to automate complex tasks such as 3-way merging viagit merge-file, hash calculation usingsha256sum/shasum, and structured data processing withjq. It also includes a normalization step that strips sensitive fields fromsettings.jsonduring the ingestion process.
Audit Metadata