The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected. The skill is limited to providing marketing strategies and image planning guidelines for e-commerce listings.
[NO_CODE]: The skill does not include any executable scripts (such as .py, .js, or .sh files) or binary components. Its functionality is derived entirely from the markdown-based instructions provided to the agent.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing user-supplied product descriptions to generate listing plans. However, since the skill does not utilize any tools for network communication, file system modification, or command execution, there are no dangerous capabilities for an attacker to exploit through injected text.
Ingestion points: User-provided product features, target audience, and listing data are processed as described in SKILL.md (Step 1).
Boundary markers: The instructions do not define explicit delimiters to separate user data from agent instructions.
Capability inventory: No evidence of network operations, file writing, or subprocess execution was found in the skill contents.
Sanitization: No input validation or sanitization is performed on user inputs.

amazon-listing-images