copywriting-awareness
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill contains deceptive or inconsistent metadata. The 'Skill Boundaries' section incorrectly describes the skill's capabilities as 'Structuring audio production workflows' and mentions 'audio engineering expertise,' which is unrelated to its primary stated purpose of Eugene Schwartz's copywriting frameworks. Additionally, the metadata field 'author' identifies 'ClawFu,' which contradicts the system-provided author context of 'guia-matthieu.'
- [INDIRECT_PROMPT_INJECTION]: The skill includes an 'Audit Existing Copy' feature that instructs the agent to analyze user-provided text. This represents a potential surface for indirect prompt injection if the ingested data contains malicious instructions.
- Ingestion points: The analysis processes text provided in the '[paste copy]' section of the prompt.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the audited text.
- Capability inventory: The skill is limited to text analysis and generation; it does not have access to file-system writes, network operations, or shell execution.
- Sanitization: No input sanitization or validation logic is defined for the content being analyzed.
Audit Metadata