The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @useclawlink/cli package from the NPM registry. This is a standard method for executing the official integration tool provided by the vendor.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the ClawLink CLI to manage Instagram actions, such as npx @useclawlink/cli login and npx @useclawlink/cli run instagram.
[CREDENTIALS_UNSAFE]: The skill mentions the storage of credentials in ~/.clawlink/credentials.json. This is the standard configuration and token storage path for the ClawLink CLI tool and is not a hardcoded secret.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it processes user-generated content from Instagram (like comments and media descriptions) that could contain malicious instructions.
Ingestion points: Data is ingested through actions like instagram_get_ig_media_comments and instagram_get_ig_user_media in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined in the skill instructions.
Capability inventory: The skill provides both read and write capabilities, including posting comments and publishing media.
Sanitization: There are no explicit sanitization steps described for handling the content retrieved from Instagram APIs.

instagram