sales-letter-writer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
  • [METADATA_POISONING]: The skill contains inconsistent metadata. The author field in the frontmatter identifies the author as 'ClawFu', which contradicts the provided vendor context of 'guia-matthieu'. Furthermore, the 'Skill Boundaries' section at the end of the file contains irrelevant references to 'audio production workflows' and 'audio engineering expertise', indicating a copy-paste error from a different skill template.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data, such as product descriptions and customer profiles, to generate marketing copy.
  • Ingestion points: Data entered via prompts like 'Improve this existing sales letter: [paste copy]' or 'Write a sales letter for my [product/service]'.
  • Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the user-provided copy.
  • Capability inventory: The skill primarily performs text generation and does not explicitly request access to high-risk tools like shell execution or network requests in its frontmatter.
  • Sanitization: No explicit sanitization or validation of the input data is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:25 PM