scrapesocial-instagram

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install a CLI tool from a public registry using 'npm install -g scrapesocial'. This is a standard installation of the vendor's own package.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using the 'scrapesocial' CLI to perform data retrieval tasks.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from external, third-party sources (Instagram). * Ingestion points: Data is ingested from Instagram profiles, posts, comments, and video transcripts via the 'scrapesocial' command outputs as described in SKILL.md and instagram-command-map.md. * Boundary markers: The skill does not include instructions to use delimiters or markers to separate untrusted data from agent instructions. * Capability inventory: The agent has the capability to execute local CLI commands ('scrapesocial') and process the resulting network-retrieved data. * Sanitization: No sanitization or validation protocols are defined to clean the external content before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 03:09 PM