gram
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the third-party
@cyberdrk/grampackage from the NPM registry to provide its core functionality. - [COMMAND_EXECUTION]: Executes the
gramCLI tool to perform Instagram operations including viewing feeds and executing engagement actions like following or commenting. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted data from Instagram.
- Ingestion points: Retrieves external content from Instagram via commands like
gram feed,gram comments, andgram post. - Boundary markers: No delimiters or protective instructions are used to separate ingested content from agent instructions.
- Capability inventory: Includes the ability to follow users, post comments, and like content through CLI commands.
- Sanitization: No sanitization or validation of the retrieved Instagram content is performed before it enters the agent's context.
Audit Metadata