ad-copy-generation-framework
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The README.md file includes a
curlcommand for manual installation of the skill definition from the author's public GitHub repository (fourteenwm/ppc-ai-skills). This is a documented distribution method for the vendor's resources and does not involve automated or hidden execution.\n- [INDIRECT_PROMPT_INJECTION]: The framework instructions in distribution.md and examples.md allow for the ingestion of external data such as customer reviews and business overviews. While this represents a data ingestion surface, the skill is restricted to theReadtool in the frontmatter and possesses no capabilities for file modification or network exfiltration, ensuring the processed data cannot trigger malicious actions.\n- [SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were found. The skill functions solely as a knowledge base for generating ad copy according to specific strategic formulas.
Audit Metadata