book-cover-designer
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions specify executing a local script
python .codex/skills/scripts/generate_book_cover.pyusing arguments derived from user input (--title,--author,--isbn). This creates a risk of command injection if the execution environment or the script itself does not properly sanitize inputs containing shell metacharacters. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted user data which is then used in script execution and file generation.
- Ingestion points: User-supplied book details including title, author names, and back-cover blurbs.
- Boundary markers: Absent; the instructions do not specify any delimiters to isolate user input from the command context.
- Capability inventory: Execution of local Python scripts and generation of HTML/JS files.
- Sanitization: Absent; no input validation or escaping procedures are described in the instructions.
- [EXTERNAL_DOWNLOADS]: The skill fetches a publisher logo from
https://cdn.lensetek.com/logo.png. This domain is associated with the skill's author ('lensetek') and is used for legitimate branding purposes.
Audit Metadata