tzai-slide
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a necessary engine via the command
npx skills add kedoupi/tzai-image-skill. This package is a resource provided by the skill author ('kedoupi'). - [COMMAND_EXECUTION]: The skill attempts to resolve the path of a local executable script named
tzai-imagewithin various hidden directories in the user's home folder (e.g.,.agents/skills/,.claude/skills/). It then executes this script using thebashcommand to generate an image file. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface. Evidence: 1. Ingestion points: Untrusted user input enters the process via the
<user subject>placeholder in SKILL.md. 2. Boundary markers: There are no delimiters or explicit instructions to the agent to ignore embedded commands within the user subject. 3. Capability inventory: The skill has the capability to execute shell commands using thebashutility. 4. Sanitization: There is no evidence of input validation or sanitization before the user subject is interpolated into the shell command string.
Audit Metadata