instagram-research

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content (captions, hashtags, and metadata) fetched from Instagram. This data is subsequently used as input for AI-driven analysis to generate content reports.
  • Ingestion points: Instagram content is retrieved via the Apify API in scripts/fetch_instagram.py and stored in local JSON files.
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the data being processed by the agent during report generation.
  • Capability inventory: The skill utilizes file system writes to store analysis results and executes Python scripts to process the data.
  • Sanitization: While scripts/analyze_posts.py performs basic regex-based cleaning for keyword extraction, there is no comprehensive sanitization of captions or metadata before they are interpolated into the final AI-generated report.
  • [COMMAND_EXECUTION]: The skill requires the execution of multiple Python scripts and bash commands to orchestrate the data fetching and analysis pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:32 AM
Security Audit — agent-trust-hub — instagram-research