lead-magnets
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md direct the agent to read external context files, which serves as an ingestion point for potentially untrusted data.
- Ingestion points: The agent is told to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within these files are provided.
- Capability inventory: The skill is restricted to generating text-based marketing strategies and plans. It does not have access to tools for file modification, network communication, or system command execution.
- Sanitization: There is no evidence of content filtering or sanitization for the ingested context data.
- [METADATA_POISONING]: The NOTICE.md file contains a future-dated copy entry (2026-10-06), which is inconsistent with the 2025 license date. This is assessed as a non-malicious typographical error.
Audit Metadata