android-design-gallery-and-signing
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a bash script
scripts/check-signing-safety.shthat performs local environment setup and auditing tasks. - The script executes
keytoolto generate a new RSA debug keystore in the user's home directory if one is not already present. - It uses
git ls-filesto scan the repository for accidentally committed sensitive files like production keystores. - It invokes
python3to format its findings into a JSON report. - [INDIRECT_PROMPT_INJECTION]: The skill's instructions require the agent to ingest and interpret external design specifications, which could be used to influence the agent's code generation behavior.
- Ingestion points: The skill is instructed to use
design/DESIGN_SYSTEM.md, HTML/CSS reference mocks, or Figma tokens (specified inSKILL.md) to define UI themes and components. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat these external design inputs as untrusted data.
- Capability inventory: The skill has the capability to execute shell commands and modify the filesystem via the included audit script.
- Sanitization: The skill lacks specific sanitization or validation rules for design tokens or external reference files before they are incorporated into the agent's logic.
Audit Metadata