kineti-fe-gdk-update
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data to guide automated code adaptations, creating a surface where malicious instructions in the data could influence the agent.
- Ingestion points: Release notes, published API definitions, and package manifest files (SKILL.md).
- Boundary markers: The instructions do not define explicit boundary markers or provide warnings to the agent to disregard instructions embedded within the external data.
- Capability inventory: The agent is authorized to execute
pnpmlifecycle scripts, use theawsCLI, and modify source files in the local repository (SKILL.md). - Sanitization: No sanitization or validation logic is specified for the external content before it is processed for adaptations.
- [COMMAND_EXECUTION]: The workflow requires the execution of multiple shell commands, including
pnpm install,pnpm run preinstall,aws sts get-caller-identity, and various CI-related verification scripts (SKILL.md). These commands are standard for library maintenance but represent a functional capability for command execution. - [EXTERNAL_DOWNLOADS]: The skill resolves library versions and fetches updates from a remote registry using the
pnpmpackage manager and authenticated AWS profiles (SKILL.md).
Audit Metadata