quote-card-maker
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text through the
--quoteparameter, which is subsequently interpolated into prompts for an image generation model. - Ingestion points: Untrusted data enters via the
--quoteargument as described inSKILL.md. - Boundary markers: The prompt template uses double quotes to delimit the quote text and attribution to the model.
- Capability inventory: The skill utilizes
Bashand interacts with image generation models (such asideogram-3-quality) to create image files. - Sanitization: No explicit sanitization or filtering is applied to the input text before it is embedded in the generated prompt.
- [COMMAND_EXECUTION]: The entry point script performs process replacement to manage its runtime environment.
- Evidence:
scripts/run.pycontains anos.execvcall:os.execv(str(_VENV_PY), [str(_VENV_PY), str(HERE), *sys.argv[1:]]). - Context: This is a routine self-bootstrapping pattern used to ensure the skill executes within its designated Python virtual environment.
Audit Metadata