oma-design
Fail
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The file
SKILL.mdcontains the pattern!bunx getdesign@latest list. This dynamic context injection executes a shell command that performs a network request to the npm registry at the moment the skill is loaded or opened by the agent. - [REMOTE_CODE_EXECUTION]: The skill executes remote code by using
bunxandnpxto run community packages (getdesign,@_davideast/stitch-mcp) that are not from trusted organizations. These packages are fetched and executed at runtime without version pinning. - [REMOTE_CODE_EXECUTION]: The
resources/getdesign-fetcher.mdfile implements a shell pipeline that dynamically resolves a tarball URL from the npm registry and pipes the remote content directly intotarfor extraction (curl -sL "$TARBALL" | tar -xzO ...). This pattern is high-risk as it processes unverified remote data streams into executable context. - [COMMAND_EXECUTION]: The skill makes extensive use of shell primitives and CLI tools including
bunx,npx,curl,tar,shasum,rm, andgcloudto perform its design management tasks. This involves significant interaction with the host operating system. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external markdown templates from a community catalog (
getdesign). Because these templates are processed by the LLM to synthesize design documents, they represent a surface for indirect prompt injection. The skill provides framing instructions to mitigate this risk, but the attack surface remains. - Ingestion points: External design templates fetched via
bunx getdesignand loaded into the context in Phase 2. - Boundary markers: The skill uses a framing prompt in
resources/getdesign-fetcher.mdto instruct the agent to treat the content as reference data only. - Capability inventory: The skill possesses file write, network (curl), and command execution (bunx/npx) capabilities across its scripts.
- Sanitization: The skill uses SHA256 hash verification to ensure template integrity against the manifest, but does not sanitize the markdown content for malicious instructions.
Recommendations
- AI detected serious security threats
Audit Metadata