persuasion-principles
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features a marketing audit function that ingests untrusted content from landing pages, emails, and advertisements. Ingestion points: Data enters the agent context through user-provided marketing materials in the 'Audit for Persuasion Gaps' section of SKILL.md. Boundary markers: There are no enforced delimiters or 'ignore embedded instructions' warnings to separate untrusted data from the system prompt. Capability inventory: The skill leverages text analysis and generation capabilities to review and rewrite content. Sanitization: No sanitization or validation of the input data is performed before processing.
- [EXTERNAL_DOWNLOADS]: The skill's frontmatter configuration specifies a dependency on the '@clawfu/mcp-skills' Node.js package for its MCP server functionality.
Audit Metadata