social-media-strategist

Warn

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill manages a sensitive GITHUB_TOKEN using a helper script (scripts/github-token.sh) that stores it in a .env file at ~/.openclaw/workspace/.env with owner-only permissions. While it avoids hardcoding, storing credentials in cleartext files within the agent workspace presents a risk if the environment is compromised.
  • [DATA_EXFILTRATION]: The report_generator.py script automatically pushes generated content plans and business strategy reports to a public GitHub repository (sorabhv/social-media-strategist). The SKILL.md instructions mark this step as mandatory and non-skippable, which causes the user's business profile details and marketing strategies to be published to a publicly accessible URL.
  • [COMMAND_EXECUTION]: The Python scripts trend_scraper.py and test_tiktok.py use subprocess.run to execute node and run the tiktok_api.mjs bridge. This pattern for dynamic execution of a separate runtime is used to fetch TikTok Creative Center data.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the tiktok-discovery-api package via npm and pytrends via pip to fetch data from external platforms.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 11:50 AM