meme-generation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes processes that involve taking user-provided text to generate images via an external API. This constitutes a surface for indirect prompt injection where malicious instructions could be embedded in the user prompt.
- Ingestion points: User-provided prompts in the
messagesarray shown in thecurlexamples inSKILL.md. - Boundary markers: No specific delimiters or "ignore previous instructions" warnings are documented in the usage examples.
- Capability inventory: The skill relies on network access to communicate with the
eachlabsAPI. - Sanitization: No sanitization or validation logic is specified in the documentation for the agent to apply to user input.
- [COMMAND_EXECUTION]: The documentation contains multiple
curlcommand examples designed to show the user how to interact with the EachLabs API. These commands are legitimate examples for the intended use of the skill and target vendor-controlled domains.
Audit Metadata