otterware-artifacts

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the otterware CLI package globally via npm. This is a vendor-owned resource associated with the author 'ckafrouni' and is required for the skill's operation.
  • [COMMAND_EXECUTION]: The skill executes various shell commands through the otterware CLI, npm, and pnpm. These are used for package management, authentication flows, and artifact management operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by reading and processing external data from artifacts.
  • Ingestion points: Untrusted data enters the agent context via the otterware artifacts read and otterware artifacts pull commands found in SKILL.md and references/cli.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within artifact content are implemented.
  • Capability inventory: The skill possesses significant capabilities, including executing shell commands, installing global packages, and writing to the local file system.
  • Sanitization: The instructions do not include steps for sanitizing or validating the content of artifacts before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:22 AM