fabled-packer-redeem-seo-content-marketing-suite

Warn

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation process involves cloning a repository from an untrusted source (github.com/FabledPackerRedeem/...) which contains the skill's logic and commands.\n- [COMMAND_EXECUTION]: The skill provides instructions for manual integration that involve sourcing a shell script (commands.sh) directly into the user's environment, allowing for potential execution of arbitrary code.\n- [CREDENTIALS_UNSAFE]: The toolkit manages multiple high-value API keys for services like Google Search Console, OpenAI, and WordPress via environment variables, which could be targeted for exfiltration if the underlying tools are compromised.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it crawls and processes content from external domains during SEO audits without explicit sanitization or boundary markers.\n
  • Ingestion points: The technical-seo and content-audit commands ingest data from external domains.\n
  • Boundary markers: None identified in the skill instructions or examples.\n
  • Capability inventory: The skill allows for network access, file writing (reports), and the execution of a broad suite of CLI tools.\n
  • Sanitization: There is no evidence of sanitization for the web content ingested during audits.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 04:51 AM
Security Audit — agent-trust-hub — fabled-packer-redeem-seo-content-marketing-suite